f86112d6758298241ab2fa84ad4f0f7b1ace35c6	d1bc743c10080fed1253686ce01749b42611ded4	2026-05-29T16:40:38+08:00	wangbomeng		add dump_pos,fix pos_tensor of pre_by_embeds
f131bf1908b8c5dd1f49d7ae7f616506fc471666	33d96dae28e17208ef61a71dba40cda3c04f135a	2026-05-27T09:38:51+08:00	wangbomeng		fix patch of qwen2.5vl,n_patch of minicpm = 64,fix n_ctx_slot,comment out M-ROPE
a43741244a646d3f8fa3ff01bb9b7d059223d0a5	b2003d6c90ef0fa26ab9e930ba3e22b355eb3d39	2026-05-15T14:39:53+08:00	wangbomeng		run llama-passkey successfully, fix llama-bench, copy 3 times input to infer qwen2.5vl
3b14ed556c15529fe1f94b649f49db7156dfaf67	dde8b8228081769c8d8f1e0751d47fa7875f8423	2026-05-14T14:34:25+08:00	Yunzhe Jia		- Removed references to CALRT from clip.h, mtmd-helper.cpp, mtmd-helper.h, mtmd.cpp, and mtmd.h. - Updated server.cpp to conditionally include CAL-LLM support. - Introduced option LLAMA_SERVER_USE_CAL_LLM in CMakeLists.txt to enable CAL-LLM integration. - Refactored server context to handle CAL-LLM requests and responses. - Updated image processing logic to remove CALRT-specific implementations. - Ensured compatibility with existing llama functionality while integrating new CAL-LLM features.
b2003d6c90ef0fa26ab9e930ba3e22b355eb3d39	7800c772d44a7415640ec1669a691232939927cf	2026-05-13T15:24:24+08:00	wangbomeng		try passkey and embedding
7800c772d44a7415640ec1669a691232939927cf	dde8b8228081769c8d8f1e0751d47fa7875f8423	2026-05-13T15:23:54+08:00	wangbomeng		try passkey and embedding
dde8b8228081769c8d8f1e0751d47fa7875f8423	fabcc7dac4b34d83fe430980bb364b81087c7ee9	2026-05-12T10:46:08+08:00	wangbomeng		clip:add minicpm patch;
5eb46fffbd2e260c540fb112314ad67bbb8f56b6	005112c51e00d998b457337ca3dad53fc46e2d0b	2026-04-24T16:24:51+08:00	wangbomeng		clip: add image_to_patches; calrt: vision copy data from bf16 to fp32
005112c51e00d998b457337ca3dad53fc46e2d0b	509670642e8090a1713f5d73590b549be827aaef	2026-04-24T16:24:31+08:00	wangbomeng		clip: add image_to_patches; calrt: vision copy data from bf16 to fp32
e24f775ee26ea5249d5ff6cd23b8a0a17fe1438d	a206460e610aef995e36e50b33e8bd41fe477541	2026-04-15T10:01:09+08:00	wangbomeng		calrt: add copy_data_to_ibuf for vision model
a206460e610aef995e36e50b33e8bd41fe477541	d8b2aaa00049978cebac15041f960d75b552f97b	2026-04-14T10:23:43+08:00	wangbomeng		calrt: support mixture of prefill_by_ids and prefill_by_embeds
6dacdd2cf9574214ca272a86674e7bd7ba21c4f0	3e6ad64467771224f072e5bad90e270951ba4cdf	2026-03-23T14:42:28+08:00	wangbomeng		calrt: add multimodal
3e6ad64467771224f072e5bad90e270951ba4cdf	b37b7d9756feb3dac2db526eeab38b572a095d47	2026-03-23T14:36:41+08:00	wangbomeng		calrt: add multimodal
d81d7b190ff5f21325167936496dfe5ab48b922e	e492f5dc8cec17529f53ef2bbdf7b502107f8148 1f5accb8d0056e6099cd5b772b1cb787dd590a13	2025-11-04T14:43:32+08:00	Yunzhe Jia		Merge branch 'master' into dev
070ff4d5356083d60b807bb34d36b31c3653a29e	bf7b0c9725ed0c406c5debaea022ec7258430634	2025-11-03T11:11:18+01:00	Xuan-Son Nguyen		mtmd: add --image-min/max-tokens (#16921)
bf7b0c9725ed0c406c5debaea022ec7258430634	fcfce040e816c542f374ad51461b3561d73c4bc9	2025-11-03T10:25:55+01:00	Xuan-Son Nguyen		mtmd: pad mask for qwen2.5vl (#16954)
bcfa87622ae46be6345a8e3dfdbdc5ba5414042b	a2054e3a8ff0da3978a4acc18c349ff58554d336	2025-11-03T00:41:08+01:00	Sascha Rogmann		feat(webui): improve LaTeX rendering with currency detection (#16508)
6b9a52422bac0f50dd8f1f8386744fa3ce9783bf	2f966b8ed87514e74bb96592217226cb6a6974dd	2025-11-02T13:08:04-08:00	Zhiyong Wang		model: add Janus Pro for image understanding (#16906)
2f966b8ed87514e74bb96592217226cb6a6974dd	cd5e3b57541ecc52421130742f4d89acbcf77cd4	2025-11-02T22:21:48+02:00	Georgi Gerganov		clip : use FA (#16837)
cf659bbb8ef9eb048e5153a27cf787fd83c05560	d8b860a219c2415faac8cc0e50b48b4aa11e3b64	2025-11-01T15:51:36+01:00	Xuan-Son Nguyen		mtmd: refactor preprocessing + support max/min pixels (#16878)
d261223d24e97f2df50220e4a5b7f0adb69bba81	dcca0d3ab840ebe9b2ccd4719033d408eeb758d7	2025-10-30T23:19:14+08:00	JJJYmmm		model: add support for qwen3vl series (#16780)
bacddc049a00786df44e682262f6e298742bfbc3	229bf686287d18f82c44e89888cc662145ecfdb4	2025-10-30T07:18:50-04:00	Tianyue-Zhao		model: Add support for CogVLM model (#15002)
144a4ce824b6bd0e48d62009d10cae1daf5308db	f549b0007dbdd683215820f7229ce180a12b191d	2025-10-29T14:09:50+01:00	Sigbjørn Skjæret		vendor : sync minja (#16500)
1c1409e13169d0ced4b1b4d39fb5b268b7525091	7a0e900e3615fa46c074a7fdf900b47d3c0a1c7e	2025-10-28T03:51:41-07:00	Sam Malayek		embedding: add raw option for --embd-output-format (#16541)
10640e31aab0819f31c1e1f2d008b019ee737232	80d28f104c0c3e61c11d6af073642b246a9fc19c	2025-10-27T21:50:22+01:00	Acly		ggml : fix interpolate with align-corners and ne=1 (#16700)
06332e28672356b964d6dfc2ba4657e20581cd43	72d53e6c4decee8b339e49aed8cc0e234b9639dc	2025-10-20T16:27:09+08:00	takuya kodama		llama-batch: fix build fails with `-Werror=missing-braces` (#16614)
7062dd8460685d6700ed7621e50a22c6f3400ca3	0398752dd450dfabdd1b9e289f6364c2600f6ab5	2025-10-20T15:44:21+08:00	takuya kodama		llama-context: only warn on pooling_type when user specified (#16674)
0398752dd450dfabdd1b9e289f6364c2600f6ab5	4f73d0a95120687e2c527739f771330a5271259a	2025-10-19T23:54:31+02:00	Giuseppe Scrivano		model : add Granite Hybrid types (#16635)
e38b7c6e9e4453e3b3e96d76e38bc2ccb6bce458	5016b7286240d29f8f640039989b84ea3a854344	2025-10-13T22:42:37+03:00	Georgi Gerganov		graph : support cacheless embeddings with FA and iSWA (#16528)
4b2dae383df708e2afc49c4859a81cd074f5ac10	41aac5c69b5fb281bc1f486afb053f78101bb39e	2025-10-12T09:29:13+03:00	Georgi Gerganov		common : update presets (#16504)
e60f01d941bc5b7fae62dd57fee4cec76ec0ea6e	81086cd6a3ca1252f0dc0f938171648399179c53	2025-10-10T22:15:05+03:00	Georgi Gerganov		server : fix division by zero when reporting stats (#16501)
56b4795842d852152222ca7a2d4304008facf1b9	2c0d875ae6c6043fbbafd2831e160955e9ca6af1	2025-10-09T14:35:22+02:00	Daniel Bevenius		model-conversion : add support for SentenceTransformers (#16387)
e08db4259521de493b7aeb49dadf29ebd1ee966a	12bbc3fa50b6df03318a4451c9a2210200a0b28d	2025-10-09T08:39:18+02:00	Saba Fallah		model: EmbeddingGemma Adding Support for SentenceTransformers Dense Modules (#16367)
b2c08c9ec4cd59ed88c1ebdd94f109af5ccc978e	7fdd16b432d247121fe5fe7b21f8805f85266c85	2025-10-08T10:57:53+03:00	Georgi Gerganov		metal : mark FA blocks (#16372)
74b8fc17f92ada295a648e3c5eb28f46bca7d892	aeaf8a36f06b5810f5ae4bbefe26edb33925cf5e	2025-10-07T13:48:56-07:00	Reese Levine		ggml webgpu: profiling, CI updates, reworking of command submission (#16452)
ef4c5b87ea2556ff8ca99cca3abdf48bdbca22f2	c61ae20d05bd4fdd8551311325a2845336449426	2025-10-07T10:32:32+03:00	Georgi Gerganov		presets : fix pooling param for embedding models (#16455)
1d6092fc72f4d10f4486ac95edfd414bc08b62b8	8ae32dc9ecd7aeebf3a5b43557e0552a0a04cd4f	2025-10-07T08:22:35+03:00	Georgi Gerganov		tests : add -INF blocks to the KQ mask in the FA tests (#16380)
c08002a1988348403a5fd59b1fa3de3a10a6f92f	3a002afafa8e06555f11aed88b02d055d8a166f3	2025-10-06T10:59:40-06:00	Gabe Goodhart		chat : Granite Docling stopping (#16438)
ca71fb9b368e3db96e028f80c4c9df6b6b370edd	35266573b968e1c947b367782fb4b3eddbb4f3c0	2025-10-05T06:57:47-06:00	Gabe Goodhart		model : Granite docling + Idefics3 preprocessing (SmolVLM) (#16206)
e29acf74fea996014380d59d31aa504ae8964258	128d522c04286e019666bd6ee4d18e3fbf8772e2	2025-10-04T11:42:56+02:00	Acly		vulkan : incremental shader builds (#16341)
ad126479c25cf983a0f994a08ba0911cf49ed62b	77233277c912d495d1069543ca540c21a2f9e5b4	2025-10-03T11:45:16+02:00	Daniel Bevenius		ci : change macos-13 to macos-15-intel (#16401)
e74c92e84236b2bab3f3c77bee4ead94928be360	b2ba81dbe07b6dbea9c96b13346c66973dede32c	2025-09-30T16:24:36-04:00	Bartowski		model : support GLM 4.6 (make a few NextN/MTP tensors not required) (#16359)
0124ac989f7e7bf08803788f66dbe4106bdcdd58	2811c65286ae954bec87049f75b86dc022006dcc	2025-09-28T19:25:58+08:00	Aaron Teo		devops: switch to using ubuntu-22.04-s390x image (#16302)
72b24d96c6888c609d562779a23787304ae4609c	624207e676ab5eb3ce7af631902bb45fb73a8359	2025-09-27T02:58:29+05:30	Vinkal		model : make minicpm embedding_scale, residual_scale and logit_scale optional with legacy defaults (#16273)
624207e676ab5eb3ce7af631902bb45fb73a8359	807e8c6d310952f2f5656afc63dab9d7083dcb5c	2025-09-27T02:03:33+08:00	Aaron Teo		devops: add s390x & ppc64le CI (#15925)
00217cd41388328c93e9e9644921c4319bb03bcc	3b337b01a1a85c2f5b49376e8c0bbdb3f521528e	2025-09-26T13:19:23+03:00	Radoslav Gerganov		ci : create git tags for released docker images (#16008)
aa3ee0eb0b80efca126cedf9bcb4fb5864b46ce3	d0991da39d3c39b3980c24cdfccb9a4c95a46870	2025-09-25T12:02:36+02:00	Daniel Bevenius		model-conversion : add embedding prompt file support (#15871)
4b9f4cb0f89a88de4bdf97727d0457b0c648804c	85e72271ba1ce78adf34fd8997803c991e617ca6	2025-09-23T13:59:34+08:00	Aaron Teo		devops: add s390x containers (#15915)
c6db9a10278f40b4b8d3f6931728f2cce2356daa	d05affbab7d1364fa7ac06c03cd33f03235ae840	2025-09-22T10:49:58+02:00	GideonSerf		embedding : fix typos in README (#16171)
3913f8730ec6d6245480affc30ae3049107956f4	76888d202ed2b835ae19ea9f9db6baf39e419297	2025-09-16T15:25:57+02:00	Daniel Bevenius		ggml : fix padding in timestep embedding kernels (#15932)
dc381aa9a6dc45f00673471d34b8bddd30e77570	10d197409bd9537ff302ad09966fe406882fef9d	2025-09-15T14:38:52-07:00	Diego Devesa		docker : enable rocWMMA in ROCm images, add gfx1151 (#15997)
b8e09f08b9a91c0401bc67d17a17c90756420346	6c019cb04e86e2dacfe62ce7666c64e9717dde1f	2025-09-14T23:00:59+02:00	Sigbjørn Skjæret		model : add grok-2 support (#15539)
9de447d94e1ae9d1a36e5a2e5bf47483352c0d9c	0f0a3c2851134d49955f3c85afbb0b1bb47c3e07	2025-09-10T17:31:40+02:00	Daniel Bevenius		ggml-cpu : fix padding in ggml_timestep_embedding (#15917)
e7b6d83b524bbc24a1343d862de6dba8e8eddbd6	2cfef4d117d67ab1dec002915b48a15d11ee1973	2025-09-10T14:17:09+02:00	Daniel Bevenius		tests : filter out no-ops from coverage report (#15900)
70cd37dbbebdb7a2f84f08207f18eabb0b291a55	acc1b008cfd95e63d5f99a370dbffb98e5a99d2c	2025-09-09T06:06:52+02:00	Daniel Bevenius		requirements : update transformers/torch for Embedding Gemma (#15828)
233d773d02c37982badddf3994e9953a175f34da	a885dcff11a7b73f9377812d6151f6b15d307de0	2025-09-08T09:44:34+02:00	Daniel Bevenius		convert : force setting sliding_window from original config (#15867)
5d6688de08e73acc2532d668380801ed79d704eb	4fd1242bef6cb2325b4ff1c1a80f3b54b64508a6	2025-09-05T04:36:23+02:00	Daniel Bevenius		model-conversion : add --embeddings flag to modelcard.template [no ci] (#15801)
fb15d649ed14ab447eeab911e0c9d21e35fb243e	856ed0947f27b4ec3ad269fceda0402fbab263d3	2025-09-04T18:10:29+02:00	Daniel Bevenius		llama : add support for EmbeddingGemma 300m (#15798)
d1e2adba65208d6de3d7f6f23b00c562ff5bb777	c1c354e44c06d259679bb5bb7a8fa9f0b28480e4	2025-09-04T15:40:44+02:00	Daniel Bevenius		llama : set n_outputs to 1 to avoid 0 outputs mean-pooling (#15791)
661ae31c9c68201577e70278285b349a5a662caf	407c23786dd0d3a503e9429eead96e611d3950c9	2025-09-03T19:59:16+02:00	Oliver Simons		CUDA: Optimize `rms_norm_f32` kernel and its fused variants, giving 1-6% perf E2E (#15715)
40a751ea9a94364da73537b86502a808ebe1fc3a	5eae9348835037046f33fafd852df7c952c95209	2025-09-03T12:50:47+02:00	Daniel Bevenius		model-conversion : remove hardcoded /bin/bash shebangs [no ci] (#15765)
8c3fdf44ecf08335942f2ba558955f55e88c7991	f6da8cb86a28f0319b40d9d2a957a26a7d875f8c	2025-09-03T09:48:35+02:00	Daniel Bevenius		model-conversion : add missing curl script [no ci] (#15761)
84ab83cc0b4b7e769451ee48e4c7d1acef91ef25	55042b3692cb1467c9ee15c62c4a9fbf180f89e3	2025-08-28T15:49:50+02:00	Sigbjørn Skjæret		model : jina-embeddings-v3 support (#13693)
46d9caa27a0281150e8cf082308c0f9e7576ebe5	5a0e3ef6f00c658fbae53797f02d5a360ebf8fec	2025-08-28T09:26:48+02:00	Daniel Bevenius		model-conversion : add mmproj conversion target (#15628)
62cef26ac5b6b7acb635d3dc963813b43952dc2b	8f5afa94c4f929da71f560db7c9f38ef6a783d95	2025-08-26T16:12:29+02:00	Daniel Bevenius		model-conversion : add qat-q4 quantization targets (#15588)
79a546220c719e6a70627b243a478ab8d84dc9e1	85cc1ae998e4898d9fa992cb9b8620338cee97bf	2025-08-26T12:54:19+02:00	Xuan-Son Nguyen		mtmd : support Kimi VL model (#15458)
c4e9239064a564de7b94ee2b401ae907235a8fca	39842a7f73012eb42816ca4f26411782bd3da7c5	2025-08-26T16:05:55+08:00	tc-mb		model : support MiniCPM-V 4.5 (#15575)
dfd9b5f6c7586c88588f06a644c131bec071a0a1	5a6bc6b1a6cb665a944426c2055794950e524bf5	2025-08-25T15:00:43+02:00	Daniel Bevenius		model-conversion : set pooling type to none in logits.cpp (#15564)
5a6bc6b1a6cb665a944426c2055794950e524bf5	6b64f74b55628e4193f4fb00313f07dbd8556528	2025-08-25T14:25:25+02:00	Daniel Bevenius		model-conversion : add model card template for embeddings [no ci] (#15557)
330c3d2d21b55bca5517db7d2eea2ea8f131df4a	e92734d51bcb82cc35f0a6b5a14928f0036b2c90	2025-08-23T01:31:54-05:00	Jeff Bolz		vulkan: optimize mul_mat_id loading row ids into shared memory (#15427)
4afb0a746f22abaa545b3ebdb76a400d7da3a713	e288693669cf9d0a71e2f2b8bd57305f06340257	2025-08-22T08:10:14Z	65a		server : Support multimodal completion and embeddings prompts in JSON format (#15108)
e288693669cf9d0a71e2f2b8bd57305f06340257	a0f98dd604d34826eb5ea2560d1e23fe726921df	2025-08-22T09:29:08+02:00	Tarek Dakhran		readme : model : mtdm : lfm2 improvements (#15476)
2758fa10dab0556e6c3f130e664750fd6773dc7c	b108e429043ee5c9fc8fa4957a0a52c3e490d5c9	2025-08-21T12:16:54+02:00	Daniel Bevenius		examples : add model conversion tool/example (#15455)
b108e429043ee5c9fc8fa4957a0a52c3e490d5c9	245be739df942861ddc52331b095b40f18e2a3f1	2025-08-21T05:06:46-05:00	Michael Giba		ci : fix -Werror=return-type in clip.cpp so ci/run.sh can run without issue (#15221)
f08c4c0d8d0cb6caaf8b7ad316039232b9fa059c	6d7f1117e3e3285d0c5c11b5ebb0439e27920082	2025-08-18T22:53:52+02:00	Xuan-Son Nguyen		mtmd : clean up clip_n_output_tokens (#15391)
f44f7931729022c57319a0124931120a169e0da9	ae532eac2c1df1d8edc3d2719145895b966de1bf	2025-08-18T03:23:56-04:00	compilade		ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors (#15379)
65349f26f2299e06477ec8e85e46243046801358	1fe00296f587dfca0957e006d146f5875b61e43d	2025-08-16T23:33:54+02:00	Tarek Dakhran		model : support vision LiquidAI LFM2-VL family (#15347)
cf9e5648a7ae02f7728fefcbcfd2979d83c96e8f	fba5c0d680b555cbac563fef57b33bc5c9621e08	2025-08-11T22:12:12+08:00	rainred		mtmd : Fix MinicpmV model converter and clip to avoid using hardcode. (#14750)
36d3f00e142696f708ab297b9f8f1c825594712d	5fd160bbd9d70b94b5b11b0001fd7f477005e4a0	2025-08-07T05:31:48+02:00	Daniel Bevenius		requirements : fix PyTorch uint64 compatibility (#15134)
ef0144c087b33e5b8da42d529ac71aaf05cb49df	2721257e3e2c4c944ac8a08221113ee7cb503f1b	2025-08-05T04:29:25+10:00	Sam		model: support GLM 4.5 family of models (#14939)
711d5e6fe66eb6cd7a10d71cec4567321848be08	f738989dcb9ccbe468c945553eafbeef7b869675	2025-08-02T05:51:02-05:00	Douglas Hanley		convert : fix Qwen3-Embedding pre-tokenizer hash (#15030)
339bd0268c498c89529cd0e90c44883c211e3745	f906275537d14c8fc7c6976d944233771fd6672c	2025-08-02T03:44:50-05:00	Douglas Hanley		model : support Qwen3-Embedding (#15023)
952a47f455fbd92e2659b98b9b6317a2dafeb532	36e5fe7bcd6640f4ff974d4c5cb04a13b5b29bce	2025-07-31T23:22:17+08:00	tc-mb		mtmd : support MiniCPM-V 4.0 (#14983)
41e78c567e9a8c652e405f4f909deb598deecd31	ad4a700117d1746799d2d6599e526e2c3a7938d2	2025-07-30T18:07:11+02:00	Daniel Bevenius		server : add support for `embd_normalize` parameter (#14964)
00131d6eaf4df029e1ec84de868c2c5957503007	1e15bfd42c3938506e0da5939bf7f42780965f01	2025-07-30T15:12:02+03:00	Georgi Gerganov		tests : update for LLAMA_SET_ROWS=1 (#14961)
a118d80233d3bf92569c051346fd2638f87bf202	61550f8231dc0aa478e2f537c5009ede6878ce22	2025-07-30T00:25:05-05:00	Douglas Hanley		embeddings: fix extraction of CLS pooling results (#14927)
749e0d27f0247337869f4698f59dd7fafba94326	64bf1c3744053cf7def10aeed21ff48883ee755b	2025-07-25T19:08:04+08:00	kiwi		mtmd : fix 32-bit narrowing issue in export-lora and mtmd clip (#14503)
3f4fc97f1d745f1d5d3c853949503136d419e6de	2df255da3cea108de0ae9b302ffdd31674b6d88d	2025-07-25T03:05:37+08:00	R0CKSTAR		musa: upgrade musa sdk to rc4.2.0 (#14498)
86f5623d904cfd392fdeb14a143097b4074660f6	39cffdf18855e0d2beba62572542251d87421e73	2025-07-24T17:50:51+08:00	yummy		llama : fix MiniCPM inference after Granite Four changes (#14850)
c8ade30036139e32108fee53d8b7164dbfda4bee	e28c0b80c249b5618c3a0d5e960f63929f380ac9	2025-07-22T12:51:03+02:00	stduhpf		Mtmd: add a way to select device for vision encoder (#14236)
b526ad2668944a7b2b1721f60679153646313831	938b785764683c298e7805e712f8728489cc2f18	2025-07-20T23:55:32+07:00	rspOverflow		Documentation: Further revisions to the Vulkan section in build.md (#14785)
21c021745d781edf9c44b4972ef6cbbf53b0ecff	b0f0ecc3dce806c68609d375a2b3edc430d8db18	2025-07-16T08:18:51-07:00	Reese Levine		ggml: Add initial WebGPU backend (#14521)
68e37a61a7b24863f67541db65b4f6195962a268	cbc68be51d88b1d5531643b926a4b359c3cff131	2025-07-16T01:11:42+09:00	Shunta Saito		model : add PLaMo-2 support (#14560)
0c1df14b5f8d992805cb22d0b77b44092a18aeab	b3ad3a0191994d6c47b2bd389d5c7431526ecd2c	2025-07-12T06:21:02-04:00	Douglas Hanley		server : fix pooled embedding output (#14645)
0aedae00e6fb48680324a5ac5da9cba0e35de6b5	6bdda13981d6c8189b7dc4f9fb8ecb91c21529f8	2025-07-10T18:20:13-06:00	Gabe Goodhart		model : Granite Four (#13550)
4a5686da22057867c23bd4a6be941ddc8c51e585	98bab638fb28cf95a5a66dd2d51b40d6c8f6d69a	2025-07-09T14:59:57-04:00	compilade		llama : support Jamba hybrid Transformer-Mamba models (#7531)
8f22dc0a53338c629c1ef8fa878d8e39bfe627c9	53903ae6fa5f1caf187889c839cdd1ad25da4018	2025-07-08T10:24:06+02:00	Xuan-Son Nguyen		model : add hunyuan moe (#14425)
e1a7059053a9b8958f2d57a21fc46dbc7fb24f8e	12f55c302b35cfe900b84c5fe67c262026af9c44	2025-07-07T23:35:35+02:00	Sigbjørn Skjæret		llama : fix incorrect minicpm3 v_states shape (#14571)
1b2aaf28acd632b79bc3b07acb5dad877dc7dbb1	343b6e94b61674ac94e64ede7b7ea3365793f7ed	2025-07-01T15:44:11+02:00	Grzegorz Grasza		Add Vulkan images to docker.md (#14472)
c839a2da1a0d4275c3a98f70c3a7627487573a46	e9b6350e61d592634263a14b3d77ecbf6c1fb096	2025-06-30T17:48:24+08:00	xiaobing318		cmake : Remove redundant include path in CMakeLists.txt (#14452)
8f52c6f8abb2ed9ad967cc0bfb90acb073011193	d2f325130c4ed77a3dcff2c23a926587fb08e2cc	2025-06-26T15:10:45+08:00	Yunzhe Jia		Squashed commit of the following:
5d5c066de8a3d2cb32f04c4d5ad1560945f30bf3	40bfa04c95c19fb42bafd4e21b5c2a7771846801	2025-06-22T21:44:57+09:00	yuiseki		mtmd : fix Pixtral OOM with large images by capping image_size to 1024 (#14326)
aa0ef5c578eef4c2adc7be1282f21bab5f3e8d26	bb16041caef45cd4348cd6f84906b5dfec7a1f6a	2025-06-21T18:12:05+02:00	Sigbjørn Skjæret		gguf-py : fix Qwen3-Embedding eos token (#14314)
edc4a29effe716956fdfd2bc5b9cba2a6d8492f8	ed3290ab34493fd3d2e0f925f816a401da4f2dfd	2025-06-19T00:08:14-05:00	Gabe Goodhart		memory : Hybrid recurrent cache (#13979)
89fea80d298184d1cd93564f48e060d9f541f4b4	6adc3c3ebc029af058ac950a8e2a825fdf18ecc6	2025-06-16T22:33:27+03:00	Georgi Gerganov		server : fix incorrect usage of llama_get_embeddings() (#14225)
d3e64b9f490cee41b7b9aa275dae2f6568ae3054	3ba0d843c6bd3faea5cf5e53dc7f3c82be20bffb	2025-06-16T14:14:00+03:00	Georgi Gerganov		llama : rework embeddings logic (#14208)
40643edb86eb10b471b0f57d4f3f7eb0e06a0df7	3cfbbdb44e08fd19429fed6cc85b982a91f0efd5	2025-06-13T17:32:56+01:00	Svetlozar Georgiev		sycl: fix docker image (#14144)
26ff3685bfbaa4c8838d7afd988b17dd5eb99f92	60c666347becacff81cd4bc9a52038ba71038e41	2025-06-13T15:17:53+02:00	ddpasa		docs : Update multimodal.md (#14122)
2c90da4c7ec694797f524042aaafbb047a7e65ff	ec9e0301fef6476df83e94842c3b625501c95566	2025-05-30T16:31:48+08:00	zhangkaihuo		llama : use llm_build_granite for minicpm (#13911)
c962ae3382a1e759c8517a229549ee53685313a1	a3938fb53d0b5183db4f5a6db21fd9122a0e4780	2025-05-28T22:33:54+08:00	Sky		server: fix remove 'image_url'/'input_audio' json-object effectlly for 'llama_params' in multimodal-model-mode (#13853)
26b79b6cb3e7840ff15729350e95907e19f9f480	1e8659e65ad0f640674d2785d02b556ab938728c	2025-05-28T10:05:54+02:00	Xuan-Son Nguyen		convert : fix tensor naming conflict for llama 4 vision (#13836)
bc583e3c63c04a11d287c108ea9e6a515ead0423	72b090da2c50e540143fd312a2f9aa5f151e6136	2025-05-27T14:06:10+02:00	Xuan-Son Nguyen		mtmd : support Qwen 2.5 Omni (input audio+vision, no audio output) (#13784)
79c137f77677b3c8ee3c60a7da033721b938399a	22229314fc46b2f741bb21b12cde71f6c6a60b52	2025-05-26T14:03:54+03:00	Georgi Gerganov		examples : allow extracting embeddings from decoder contexts (#13797)
40aaa8a403df5dcfb515eb2fd7a817fd99779526	a08c1d2845dc279d58d826ef3c3ecad97cbbcef7	2025-05-25T14:06:32+02:00	Xuan-Son Nguyen		mtmd : add support for Qwen2-Audio and SeaLLM-Audio (#13760)
a08c1d2845dc279d58d826ef3c3ecad97cbbcef7	d785f9c1fd1a1929c6d0e2a0b12cae5db867908b	2025-05-25T14:04:49+02:00	ddpasa		docs : add Moondream2 pre-quantized link (#13745)
4032ca406632212b075e3c61c2a4476128321410	515fdbf7ed839dfe6a24aeb6225936609a7f6d6d	2025-05-25T10:29:43+02:00	Piotr Jasiukajtis		llama : add support for Qwen3 MoE tied word embeddings (#13768)
cc74d5be990e37f201591fd868a92e64abdbf902	5be24af73d77ea23d399726f1d2a01a70ee86331	2025-05-22T16:33:39+03:00	Georgi Gerganov		server : pad small embedding batches (#13692)
92ecdcc06a4c405a415bcaa0cb772bc560aa23b1	f71f40a2847d4c9f57b86cd206e0a27b2bfb6d1c	2025-05-19T13:04:14+02:00	Xuan-Son Nguyen		mtmd : add vision support for llama 4 (#13282)
3cc1f1f1d24472a6558c942b1c78989ff4b0e569	c753d7bed0dc2cc2d5c42dfa9806cba91748392e	2025-05-15T14:24:50+02:00	Xuan-Son Nguyen		webui : handle PDF input (as text or image) + convert pasted long content to file (#13562)
d486dd3e8ecfba0170f8632a1530540de560f4a3	21ca987fba504d273ea28ebc4d3e5b3736a11c8e	2025-05-14T10:07:31+02:00	Luca Stefani		webui: Allow pasting file from clipboard (#13526)
21ca987fba504d273ea28ebc4d3e5b3736a11c8e	be1d4a13db26750fac702ceb3af88ae4f39dc9f4	2025-05-14T09:59:12+02:00	ddpasa		docs: Update link to ggml-org in multimodal.md (#13513)
71bdbdb58757d508557e6d8b387f666cdfb25c5e	f0995d28ce3d15095b6845d94ce4465e46575873	2025-05-13T17:07:21+02:00	Xuan-Son Nguyen		clip : clip.h become private API (⚠️ breaking change) (#13510)
b4726345aca49e2ad62d615e6e370b3dbad6434f	bf7937112058f2815fc3825a9ff7b536ecafa3bb	2025-05-13T15:33:58+02:00	Xuan-Son Nguyen		mtmd : remove libllava, remove clip-quantize-cli (⚠️ breaking change) (#13460)
de4c07f93783a1a96456a44dc16b9db538ee1618	10d2af0eaa0aafd7c6577b279dfa5221ff44a63f	2025-05-12T15:06:51+02:00	Xuan-Son Nguyen		clip : cap max image size 1024 for qwen vl model (#13478)
3eac209319a6726fd9687c6188fc6b916b65953d	a634d75d1bb4034b8c945042ceea268b5b895730	2025-05-11T11:35:52+02:00	City		mtmd : support InternVL 3 38B and 78B mmproj (#13443)
15e6125a397f6086c1dfdf7584acdb7c730313dc	3b24d26c22b9d92b5aa39930988700c84e524cf4	2025-05-10T19:57:54+02:00	Xuan-Son Nguyen		mtmd : add hard limit on image resolution for qwen2vl / qwen2.5vl (#13434)
33eff4024084d1f0c8441b79f7208a52fad79858	17512a94d636c4b6c1332370acb3e5af3ca70918	2025-05-09T19:29:37+02:00	Xuan-Son Nguyen		 server : vision support via libmtmd (#12898)
d9c4accaff30926e8a5fd8a2429e549158a845e0	15e03282bb432631193464100c2237a3b6bcfe4c	2025-05-09T09:06:37+02:00	Xuan-Son Nguyen		server : (webui) rename has_multimodal --> modalities (#13393)
f05a6d71a0f3dbf0730b56a1abbad41c0f42e63d	ee01d71e585f4a17ae83ec55d77acfdcf0bfa798	2025-05-08T14:25:39-04:00	Matt Clayton		mtmd : Expose helper_decode_image_chunk (#13366)
8c83449cb780c201839653812681c3a4cf17feed	1a844be132dbe865358e1de81136920c1d35ac73	2025-05-08T15:37:29+02:00	Xuan-Son Nguyen		server : (webui) revamp the input area, plus many small UI improvements (#13365)
6562e5a4d6c58326dcd79002ea396d4141f1b18e	51fb96b1ff2e1cc98b2492a012b7d93531a6a9a8	2025-05-08T14:28:33+03:00	Georgi Gerganov		context : allow cache-less context for embeddings (#13108)
814f795e063c257f33b921eab4073484238a151a	d879433824ac3c16b3b5f00075895d0ee9688e34	2025-05-07T16:36:33+02:00	Diego Devesa		docker : disable arm64 and intel images (#13356)
6c7fd67b647a76846d1691cd181011dff4549d02	141a908a59bbc68ceae3bf090b850e33322a2ca9	2025-05-07T15:23:11+08:00	piDack		llama : support tie embedding for chatglm models (#13328)
32916a49072f01c43e20df374af5f8a1f70d6963	ffc727203af1061fdeb49efef30f76171722e403	2025-05-06T22:40:24+02:00	Xuan-Son Nguyen		clip : refactor graph builder (#13321)
5215b91e9377ce23e4ccc92ec3156bf5c7f892a3	ae803bfc3d0fc2d0d3e1cce22ee103a30939e104	2025-05-05T12:54:44+02:00	Xuan-Son Nguyen		clip :  fix confused naming ffn_up and ffn_down (#13290)
27aa2595321c4d9cc4086a8e67bdea204b8309b0	9fdfcdaeddd1ef57c6d041b89cd8fb7048a0f028	2025-05-04T23:43:42+02:00	Xuan-Son Nguyen		mtmd : add C public API (#13184)
36667c8edcded08063ed51c7d57e9e086bbfc903	3bf785f3efa89ed28294fbf73054558a2b034bfb	2025-05-03T20:07:54+02:00	Xuan-Son Nguyen		clip : revert the change of BOI/EOI token for GLM-edge (⚠️ breaking change) (#13259)
2f567611c0234bbca0a4009762acb47b56866095	7d2123484e6ba8fcd90fff8c01661b9dbbefdc9d	2025-05-02T11:42:30-04:00	Jared Van Bortel		llama-model : support Qwen2 embedding models and pooling_mode_lasttoken (#13245)
7d2123484e6ba8fcd90fff8c01661b9dbbefdc9d	074e42ab31de4c99aa7d9d2d239660f64b2380d6	2025-05-02T11:41:54-04:00	Jared Van Bortel		convert : use correct context length for nomic-embed-text-v2 (#13216)
074e42ab31de4c99aa7d9d2d239660f64b2380d6	c642bc014c105728ce45015813351dc5a37f60a2	2025-05-02T17:17:15+02:00	Xuan-Son Nguyen		convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf (#13209)
e84773ab604fe0d935d03741df003716398dc57b	fab647e8842c5f80da7e8f2c625dab6a0e19e5d4	2025-05-02T14:20:27+06:00	Shakil Ahmed		mtmd-cli : fix out_of_range when input image path is empty (#13244)
b6e4ff69b8abd509647b531bd5b4e86950204f66	e0f572c8466e70d35cbd70ee536ad8fc83b2acac	2025-05-01T21:32:21+02:00	Loïc Carrère		clip : (minicpmv) Re-enable upscaling of images smaller than the CLIP image size (#13237)
b5769d92b4510c77691ad9e3f8b643c2ba202e53	8936784f7a1ec4f91637d04b77fdc90ec36ebac9	2025-04-29T15:47:55+02:00	Daniel Bevenius		ggml : suppress Windows compiler warnings (whisper/3075)
8936784f7a1ec4f91637d04b77fdc90ec36ebac9	13c9a3319b65469e883c49dd1c478abedc410157	2025-05-01T17:05:42+02:00	Xuan-Son Nguyen		mtmd : add **vision** support for Mistral Small 3.1 (#13231)
a70183eb0079fdf6ebeaed12966338a039461b5d	8d33d740c308fe0049515668aac0e561269afe9e	2025-05-01T03:09:41-04:00	Jared Van Bortel		llama-model : fix the reported size class for nomic-embed-text-v2-moe (#13223)
3e168bede4d27b35656ab8026015b87659ecbec2	ceda28ef8e310a8dee60bf275077a3eedae8e36c	2025-04-30T16:56:24+02:00	Xuan-Son Nguyen		convert : improve model arch handling (#13122)
07c2e2f76cce9a61c110b6995fbb90ccea2c3aaa	44cd8d91ff2c9e4a0f2e3151f8d6f04c928e2571	2025-04-30T13:06:15+02:00	Xuan-Son Nguyen		convert : correct typo image_mean --> image_std (#13208)
00e3e5a194e88e604e7c91391b9e90332888fd72	e98b3692be4cd8fbbd9a56fbacc2f2bf0bf26a68	2025-04-29T11:47:04+02:00	Xuan-Son Nguyen		mtmd : add qwen2vl and qwen2.5vl (#13141)
5f5e39e1ba5dbea814e41f2a15e035d749a520bc	eaea3253244dc4bbe07f6cd81325847ccc6cf93e	2025-04-28T15:52:15-04:00	AT		model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture (#12466)
eaea3253244dc4bbe07f6cd81325847ccc6cf93e	43ddab6eeeaab5a04fe5a364af0bafb0e4d35065	2025-04-28T21:23:19+02:00	Xuan-Son Nguyen		clip : fix model size display (#13153)
5fa9e63be82225fb3249c76f39ddda3e5bdec0a3	a4c340f974f9b7ac0c1aae897aabaa54549a97e5	2025-04-28T12:18:59+02:00	Xuan-Son Nguyen		clip : refactor set input for cgraph + fix qwen2.5vl input (#13136)
59e991c23cc44cb5fb657e7b9358cac21fb79828	ca2bb89eac2097ab4620448737e58af8452e444b	2025-04-27T18:43:37+08:00	LostRuins Concedo		Fixes Qwen2.5VL segfault during inference with https://github.com/ggml-org/llama.cpp/pull/12402 as has_qwen2vl_merger migration was incomplete (#13133)
ca2bb89eac2097ab4620448737e58af8452e444b	2d451c80590b9ac250322769ac13d3b4870dbcf7	2025-04-27T16:10:34+08:00	HimariO		clip : Add Qwen2.5VL support (#12402)
4753791e70acd4d4e02f2098f14a03df26c992bd	77d5e9a76a7b4a8a7c5bf9cf6ebef91860123cba	2025-04-26T22:39:47+02:00	Xuan-Son Nguyen		clip : improve projector naming (#13118)
edb18b6e8f5ea6509ad43057f8bb98fc557dbc4e	514c45608f93f66106a712dee1abe062099ce790	2025-04-25T14:31:42+02:00	Xuan-Son Nguyen		clip : fix pixtral on some GPU backends (#13097)
13be08daf992c89d5169518229b3740041c0f419	226251ed56b85190e18a1cca963c45b888f4953c	2025-04-24T22:17:04+02:00	Xuan-Son Nguyen		clip : remove boi/eoi embeddings for GLM-edge model (#13081)
226251ed56b85190e18a1cca963c45b888f4953c	87616f0680947800ecba3e9f6bc6e101943bf8e6	2025-04-24T22:29:22+03:00	Georgi Gerganov		embeddings : fix batch sizes (#13076)
56304069599f4dd9749d94b9bca2c2c65bb27c02	ecda2ec4b347031a9b8a89ee2efc664ce63f599c	2025-04-24T02:32:35+05:00	pl752		llama-mtmd-cli: Sigint rework in mtmd vision example (#13080)
ecda2ec4b347031a9b8a89ee2efc664ce63f599c	eb1776b15a32d832f1266deeeab75b9d255c5849	2025-04-23T20:21:59+02:00	Xuan-Son Nguyen		mtmd : Support Pixtral 12B (#13065)
84a9bf2fc2875205f0806fbbfbb66dc67204094c	2016f07bd106c73699ecbaace80f55db5ed95dac	2025-04-21T15:32:58+02:00	Xuan-Son Nguyen		mtmd : merge llava, gemma3 and minicpmv CLI into single `llama-mtmd-cli` (#13012)
2016f07bd106c73699ecbaace80f55db5ed95dac	6602304814e679cc8c162bb760a034aceb4f8965	2025-04-20T23:29:36+02:00	Xuan-Son Nguyen		convert : experimental support for `--mmproj` flag (#13023)
6602304814e679cc8c162bb760a034aceb4f8965	66168204be9559dc841f06f0025f3da01d9a8546	2025-04-20T03:15:41-07:00	Jeffrey Morgan		llava: fix errors in clip.h on certain compilers (#13030)
37b9f0d29d7301dd0ec5dfae8f357ccee96325d7	6408210082cc0a61b992b487be7e2ff2efbb9e36	2025-04-19T09:15:45+02:00	Xuan-Son Nguyen		clip : refactor, add `image_manipulation` and `llava_uhd` classes (#13011)
b9154ecff93ff54dc554411eb844a2a654be49f2	2db9ba1464f3de0aceb2b5289963e69fc369cb66	2025-04-18T10:04:51+02:00	Xuan-Son Nguyen		mtmd : add methods to access `mtmd_image_tokens` (#12906)
510676475f885ec064ff147af9f20ee7a9b12a50	daa422881a0ec7944771bcc8ff8de34d11f5bd3b	2025-04-15T14:07:42+05:30	Akarshan Biswas		SYCL: Add ROPE vision kernel (#12887)
daa422881a0ec7944771bcc8ff8de34d11f5bd3b	eccc7a1602f0752507de4aaad1008b9618a282c8	2025-04-15T07:49:57+01:00	Juk Armstrong		llama : DeepSeek V2/V3 MLA implementation (#12801)
e59ea539b83d2c7947c99bd350549364dbba450c	c94085df2871d2cad11f6411304d7798d7dd4cdd	2025-04-12T01:29:03-04:00	Matt Clayton		llava: Fix cpu-only clip image encoding sefault (#12907)
0c509239445088f21265580b86733c5b184261d9	fccf9cae83e6c6cd31a0ecb403d237638e427d0a	2025-04-11T12:09:39+02:00	Xuan-Son Nguyen		clip : use smart pointer (⚠️ breaking change) (#12869)
12e9158f25cb47e97ca9b8083e1ec7415f262260	5b1f13cb64dbb0de7e95dae86725928d350c188c	2025-04-11T09:24:34+02:00	Daniel Bevenius		xcf : add check for visionos build version (#12854)
b0091ecc1e5c0f689be856fade3803a534f35c9f	31f7803bc4e7c0dcc279ee04c2ecfb76b2afdd3e	2025-04-09T23:17:12Z	Rudi Servo		docker : added all CPU to GPU images (#12749)
d9a63b2f2e91cdcb0eda211b7f49fadcdea0f664	8ed71242f464dc0a3fb3cffcfe064e55bdec72f9	2025-04-09T17:22:30+08:00	R0CKSTAR		musa: enable freediskspace for docker image build (#12839)
65a69e6e1b6d55cd5f78f8bcdfaba8a8c59a8d96	47277d6d1d0d515cff34292a1a78a0d1b7252350	2025-04-09T10:09:53+02:00	Xuan-Son Nguyen		clip : do not print ftype (#12832)
b32efad2bc42460637c3a364c9554ea8217b3d7f	a19b5cef16d885c44c635da4a5c97113c1577de8	2025-04-08T16:01:58-04:00	Matt Clayton		llava: improve clip_ctx destructor to not memleak load_image_size (#12834)
a19b5cef16d885c44c635da4a5c97113c1577de8	78a1ba0a4f2bfed5b8b8e312592143d22e531698	2025-04-08T19:54:51+03:00	Georgi Gerganov		llama : fix FA when KV cache is not used (i.e. embeddings) (#12825)
2dabf759e7c8c827d38cdd18d0792070e6a4f4e1	1d343b4069c74b2c7b19ae84260cd98aa2320a9a	2025-04-08T21:49:13+08:00	dm4		llava: add more helper functions to check projector types in clip context (#12824)
0364178ca2452bd241a4cdd4350d0d7a6ff8c4b4	c6ff5d2a8da2587cc78c9ede9171dfc3f076c757	2025-04-05T17:17:40+02:00	Xuan-Son Nguyen		clip : refactor clip_init, add tests (#12757)
f52d59d771dc231fc2ac39adacf157ddefc97730	52de2e594979be52f0da92601747aa44a13e50e4	2025-03-31T11:07:07+02:00	Sigbjørn Skjæret		llava : fix clip loading GGUFs with missing description (#12660)
5dec47dcd411fdf815a3708fd6194e2b13d19006	f125b8dccff34439a26bf750c9edef358c48c1f8	2025-03-27T08:08:08-07:00	lhez		opencl: add multi and vision rope, `gelu_quick` and `im2col` (#12600)
02082f1519565fc7b49de211b28bc5404a69209b	df4d20cd53d5bb6fc21c1dc65f026d53b566d097	2025-03-26T22:06:04+08:00	Ivy233		clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA backend (#12566)
2b65ae30299b9c67e25c51ee567e9a2ef22279ab	48d7021c61ceda6fcf1a7294d2115b8e1a53ae95	2025-03-24T09:20:47-07:00	lhez		opencl: simplify kernel embedding logic in cmakefile (#12503)
0fd8487b142b2b92565bc95b39ddc440955a237c	108e53c2f1b57b79c8bcf9773fba5a82e2f1eeb5	2025-03-19T10:15:23Z	Guus Waals		Fix visionOS build and add CI (#12415)
108e53c2f1b57b79c8bcf9773fba5a82e2f1eeb5	a686171ea71ed8cb8a324850d146cb65a001e141	2025-03-19T09:08:49+01:00	Sigbjørn Skjæret		llama : add support for GPT2, Bloom and CodeShell tied word embeddings (#12456)
99aa304fb900654ec338749f64e62895b9a88afd	8551c44d840a7db50adb958ccaf464dc3ded82e7	2025-03-18T17:24:33+01:00	Xuan-Son Nguyen		llama : add support for EXAONE tied word embeddings (#12451)
7841fc723e059d1fd9640e5c0ef19050fcc7c698	bf69cfe62f9ccc01112c0232a55820b95a8c1fda	2025-03-12T09:30:24+01:00	Xuan-Son Nguyen		llama : Add Gemma 3 support (+ experimental vision capability) (#12343)
96e1280839561aaabb73851f94972a2cd37b2d96	2c9f833d17bb5b8ea89dec663b072b5420fc5438	2025-03-11T09:20:16+01:00	Xuan-Son Nguyen		clip : bring back GPU support (#12322)
8352cdc87b207a735d34c431a36c425728cb4586	1e2f78a00450593e2dfa458796fcdd9987300dfc	2025-03-10T16:33:24+08:00	tc-mb		llava : fix bug in minicpm-v code (#11513)
5e2d57b2b2e43eadbe6d66ba3e873a824b95e725	f1648e91cf6c52e9593810aa70857e412d474c09	2025-03-07T15:35:57+08:00	BB-fat		metal : simplify kernel arguments using a struct (#3229) (#12194)
d6c95b0740510231b3797b80d6d3440d8fe188b6	d76a86d967ef491d530400b08bc8ef8a14807936	2025-03-07T06:23:16+01:00	Daniel Bevenius		metal : fix default.metallib build (#12224)
e9b2f84f145fbd458dcb98f227bd09370918be6e	e721c05c9336a72fbb59d5c75967360bc67036c6	2025-03-06T16:33:21+08:00	Aaron Teo		llava: add big-endian conversion for image encoder (#12218)
16e4b22c5e58ee200ede913fd7b7b8ba92132ce8	074c4fd39df3af974e10fbee6cc6db5d9304655b	2025-03-05T17:16:01+02:00	Plamen Minev		ggml : fix GGMLMetalClass ODR (#12200)
a057897ad4e48e3df0354256e0cc80dadcb57595	5bbe6a9fe9a8796a9389c85accec89dbc4d91e39	2025-03-05T06:30:31+01:00	Daniel Bevenius		llama : add xcframework build script (#11996)
84d5f4bc195b9540fcb902d869015fba7ef6baa4	438a83926afcff3643ffef5543db67545ceffe39	2025-02-28T04:31:47-07:00	Alex Brooks		Update granite vision docs for 3.2 model (#12105)
4d1051a40ffc2fdff80bc532eea5b9568b85c156	3e9a2860e996657fc10db8393cf65adc40703082	2025-02-25T02:46:05-07:00	Alex Brooks		Add Doc for Converting Granite Vision -> GGUF (#12006)
7a2c913e66353362d7f28d612fd3c9d51a831eda	08d5986290cc42d2c52739e046642b8252f97e4b	2025-02-24T09:09:51-07:00	Alex Brooks		llava : Add Granite Vision Support (#11794)
36c258ee921dbb5c96bdc57c0872e4a9a129bef6	f3e64859edb0d55d4223ead78672597cd1a218df	2025-02-22T22:28:28+08:00	Ting Lou		llava: build clip image from pixels (#11999)
ee02ad02c56ff36a5edd22d8617ab3f9546ce7fe	c392e5094deaf2d1a7c18683214f007fad3fe42b	2025-02-20T23:11:03-07:00	Alex Brooks		clip : fix visual encoders with no CLS (#11982)
bf42a23d0a515a508aecf10fde1d52c5ed5104c6	c2ea16f260445d1f2bd9fee78fb8acb2b3aaaad4	2025-02-16T01:52:23-06:00	Jeff Bolz		vulkan: support multi/vision rope, and noncontiguous rope (#11902)
b7552cfcbc7defccd8bdefd0a7b9c47d145ed3d7	225bbbfa39930cda38a2e5d1f3e5b38226732009	2025-02-07T09:15:22+01:00	Daniel Bevenius		common : add default embeddings presets (#11677)
902368a06b915b860236cfc97ff885b2aceae256	c3db0480bb820e120249014b380e1f4badf2a1c1	2025-02-05T19:52:31-06:00	Charles Duffy		metal : avoid breaking build when metal API predates TARGET_OS_VISION (#11690)
1ec208083cb896dd8772a2f962151fa3d4a74e36	9f4cc8f8d310b13ab3fc93a9be81b1d1376a7fa6	2025-02-05T14:45:40+07:00	SAMI		llava: add quantization for the visual projector LLAVA, Qwen2VL (#11644)
0cec062a638700495673f5494d200b74340538be	53debe6f3c9cca87e9520a83ee8c14d88977afa4	2025-02-02T15:48:46+08:00	piDack		llama : add support for GLM-Edge and GLM-Edge-V series models (#10573)
b636228c0ad0db95bf73008094c6145a05615cf6	325afb370a1a7b32b5fe46a749bc840c66db9765	2025-01-29T09:38:54+01:00	Daniel Bevenius		embedding : enable --no-warmup option (#11475)
f643120bad8ab3a753daa64aaac8288ee5800e06	6e84b0ab8e10b8f6f99a32855f976ebcd35b0353	2025-01-28T11:42:32+01:00	Nuno		docker: add perplexity and bench commands to full image (#11438)
466ea66f338d63109540dae1df97ccfdbf4cd08f	5f0db9522f347b095f84c3033d6c1c1895402e25	2025-01-25T07:26:01+08:00	jiahao su		CANN: Add Ascend CANN build ci (#10217)
3e3357fd77bcf5bd8cfcc53ca53d4a5532e67e1b	6171c9d25820ccf676b243c172868819d882848f	2025-01-22T15:35:48+08:00	tc-mb		llava : support Minicpm-omni (#11289)
8f70fc3d1b1d3c17b61842330dd106d391cc1227	1244cdcf14900dd199907b13f25d9c91a507f578	2025-01-13T13:38:20+01:00	Daniel Bevenius		llama : remove 'd' from bad special token log (#11212)
2739a71e4b88474833b64aa974ca4515574fd3c4	ba8a1f9c5b675459c55a83e3f97f10df3a66c788	2025-01-11T05:50:33+01:00	Daniel Bevenius		convert : sort print supported models [no ci] (#11179)
ff3fcabc727b2dd0c477d23a258217b27cc639fb	c3f9d25706ac84297067aeaa662c1f1af42ed443	2025-01-10T11:30:53+01:00	Daniel Bevenius		convert : add --print-supported-models option (#11172)
5e3b08d606b5b0caaea16541b504c3bba8f3ec1d	db68c93b57bfdf6da1fbdae81080382d6998cbc9	2025-01-04T10:53:54+02:00	Georgi Gerganov		ggml : do not install metal source when embed library (ggml/1054)
9ba399dfa7f115effc63d48e6860a94c9faa31b2	2cd43f4900ba0e34124fdcbf02a7f9df25a10a3d	2024-12-24T21:33:04+01:00	Reza Kakhki		server : add support for "encoding_format": "base64" to the */embeddings endpoints (#10967)
0ca416c91aea4549d9c77e3efeca403e15aa6c75	21ae3b9be83820565d1a720999b7f63ce95b4920	2024-12-20T14:12:06+01:00	Xuan Son Nguyen		server : (UI) fix copy to clipboard function (#10916)
d408bb9268a988c5a60a5746d3a6430386e7604d	5cab3e4aaa892df4620b720f20a503a1bbbe7a52	2024-12-19T18:47:15+02:00	Georgi Gerganov		clip : disable GPU support (#10896)
2fffc52b50992ac5bc64db19d33c39cbc06f52cf	7585edbdebd02861e0994dae67c9338731fb3fc5	2024-12-19T06:04:51-07:00	Sukriti Sharma		llama : fix Roberta embeddings (#10856)
0bf2d10c5514ff61b99897a4a5054f846e384e1e	7bbb5acf125d1d2840cac7d31b9aaa72210dd5ec	2024-12-18T19:27:21+02:00	Georgi Gerganov		tts : add OuteTTS support (#10784)
152610eda91217ac409342cd976d05f5114ad39f	0e70ba686e6c717a0aa41d88284e2a392c2bd0cd	2024-12-18T13:01:41+02:00	Georgi Gerganov		server : output embeddings for all tokens when pooling = none (#10861)
46828872c31b25df16169cbbf5c2225fa9cb0675	6b064c92b4c0228e333193c167f2c98d2ec8d9bc	2024-12-18T09:55:09+01:00	Xuan Son Nguyen		server : (embeddings) using same format for "input" and "content" (#10872)
8dd19a48129d578972ea3d98896edbbf492891a9	130d0c90bd26b25e3a713b17a61a5d4eb0a66405	2024-12-16T19:34:38+09:00	gn64		vulkan : fix soft_max.comp division by zero (whisper/2633)
05c3a444b8b017b01b366b725ba22c740aae6b38	382bc7f2e8ffd0b89f23e840d097e21f301197ba	2024-12-17T16:00:24Z	krystiancha		server : fill usage info in embeddings and rerank responses (#10852)
ba1cb19cdd0d92e012e0f6e009e0620f854b6afd	56eea0781cbd2608ed8ff524955495569b9264be	2024-12-14T20:43:46+08:00	HimariO		llama : add Qwen2VL support + multimodal RoPE (#10361)
a76c56fa1a3d27467eb97468d8c3b2fe1243b61a	c27ac678dd393af0da9b8acf10266e760c8a0912	2024-12-13T12:23:52-08:00	lhez		Introducing experimental OpenCL backend with support for Qualcomm Adreno GPUs (#10693)
11e07fd63bac1cb642380a7a3eac03fd8703e948	4601a8bb6784d2ab8b4b605354b51979fbeea1d3	2024-12-13T18:23:50+01:00	Corentin REGAL		fix: graceful shutdown for Docker images (#10815)
784a14aa496a66cc43e76014a1bf4333b4a2a55a	c5ede3849fc021174862f9c0bf8273808d8f0d39	2024-12-07T00:02:14-07:00	Sukriti Sharma		convert : add support for Roberta embeddings (#10695)
8d0cfd554a9ae545ff94d27e04458f537b4e8c0e	2759916d86b70e7aceaed4d0b4e7ed126f0f9e51	2024-12-04T17:42:50+08:00	JFLFY2255		llama: Support MiniCPM-1B (with & w/o longrope) (#10559)
01e6d9bb71eb71fe1f811f2fdef15753232cd0f2	cc98896db858df7aa40d0e16a505883ef196a482	2024-12-04T08:26:37+08:00	piDack		clip : add sycl support (#10574)
7db3846a94ce7683b3e8120abe427457edf840c9	c6807b3f28cc3dbfda3ec390bcb87e69fb5634e2	2024-11-26T13:05:20+01:00	Diego Devesa		ci : publish the docker images created during scheduled runs (#10515)
50d5cecbda3b0d03344eed326287adc1f6c7f3ef	9fd8c2687f5aa2f095ac6e12a376e1c0583888e8	2024-11-25T22:05:39+01:00	Diego Devesa		ci : build docker images only once daily (#10503)
9336db462c0c34bbe2055413fe4e16442626c38b	96fa2c5e2d6cb5319f34c3a7fb0cec05694b22f1	2024-11-24T02:02:34-07:00	Gabe Goodhart		convert : XLMRoberta Type Vocab Size (#10458)
57f8355b29a8c7dfcd1fb6094758ad85644f8535	9901068ac78838745e604fffb4601d315a610456	2024-11-15T12:10:45+01:00	Romain Biessy		sycl: Update Intel docker images to use DPC++ 2025.0 (#10305)
5b359bb1e3585de45bec79fd6c18934897662cdf	e89213492d3e01705739789733f0f2d250b4c449	2024-11-09T15:35:46+08:00	SXX		ggml: fix zero division in ‘dne’ calculation in CUDA COUNT_EQUAL operator when ‘ne’ is small (#10213)
d05b3127bd30515955aa4ee2bacdb68ebafe88f4	76c6e7f10551960e4ec9e14e0535b72081f1c7ad	2024-11-08T17:34:06+08:00	Jhen-Jie Hong		swift : exclude ggml-metal-embed.metal (#10211)
a71d81cf8c1afb26b166f897c94ee1581f9fac7d	eec4d71737b32f312e0082b671629a0368e1a20d	2024-11-07T17:31:10-04:00	Xuan Son Nguyen		server : revamp chat UI with vuejs and daisyui (#10175)
8f275a7c4593aa34147595a90282cf950a853690	8d8ff715367480b856ad86ac3888e9742b13a6fa	2024-10-29T17:52:56+09:00	Changyeon Kim		ggml: Add POOL2D OP for GPU acceleration to the Vulkan backend in the MobileVLM model. (#9763)
674804a99617b4f90292b4080ecab450ea3d30ba	e94a138d644a9b34da61805f7aeb8af595c61b53	2024-10-22T09:40:02+02:00	Daniel Bevenius		arg : fix typo in embeddings argument help [no ci] (#9994)
cf8e0a3bb9c0e93e371773b282054cdbbb231038	c7499c557cc1efafaf0a6bc12963c39826299703	2024-10-11T02:10:37+08:00	R0CKSTAR		musa: add docker image support (#9685)
1927378bcce20ba72b6c89d5977b854a4bcaeb5d	6f1d9d71f4c568778a7637ff6582e6f6ba5fb9d3	2024-10-01T02:31:36-04:00	compilade		convert : refactor rope_freqs generation (#9396)
f4d2b8846a6b34419ff9e9491aee6cd95e444bfc	1b2f992cd2cff0b69e5abe78bb8888d51ed19d67	2024-09-28T17:42:03+03:00	Georgi Gerganov		llama : add reranking support (#9510)
9a913110cf471a8287ac06c43cbe307d3cf6df99	43bcdd9703ec19af7d2a519640b5ed6f4aac3d53	2024-09-28T12:08:43Z	nopperl		llama : add support for Chameleon (#8543)
0b3bf966f47bf2ba88e5d4e3ed429602008c7e63	f0c7b5edf82aa200656fd88c11ae3a805d7130bf	2024-09-23T22:23:54+02:00	Xuan Son Nguyen		server : add --no-context-shift option (#9607)
acb2c32c336ce60d765bb189563cc216e57e9fc2	a6a3a5c531c73aef85750a847d21e7d4671e723d	2024-09-16T13:07:13+02:00	Daniel Bevenius		llama : rename n_embed to n_embd in rwkv6_time_mix (#9504)
95ca85168b5b089b80a811b59528ce0a2f1bd1dd	441b72b91f818fe69497e5816f87969e90c73c43	2024-09-16T14:45:20+08:00	CarryFun		llama : support MiniCPM3 (#9322)
1b28061400eb9832603c9f1dfbec4d339a8490a2	8db003a19d7055b5bd248ce2afff9324e5b8da95	2024-09-11T17:52:13+02:00	slaren		llama : skip token bounds check when evaluating embeddings (#9437)
0996c5597f680effacc046832bb807c14900e22d	5bb2c5dbd26b246d334f0087b3cbd800f2e65c54	2024-09-11T12:59:13+02:00	Xuan Son Nguyen		llava : correct args for minicpmv-cli (#9429)
6c89eb0b4749184f4d19e96ada5dcb8847129b9c	9b2c24c0993487d3b34a873980e292da571481f3	2024-09-07T09:48:54+02:00	slaren		ci : disable rocm image creation (#9340)
9bc6db28d011d47a5f318dc4aebbe7927fac4629	32b2ec88bc44b086f3807c739daf28a1613abde1	2024-09-05T21:48:47-04:00	compilade		ggml-quants : ternary packing for TriLMs and BitNet b1.58 (#8151)
048de848ee4baad4531fcd6239438f5d55be365c	f771d064a95d212ddadea452ad0cc1e42b2c3db3	2024-09-02T18:11:13+02:00	slaren		docker : fix missing binaries in full-cuda image (#9278)
6e7d133a5f9409dd257fad90d7f320721b07a1b2	b60074f1c26d8354053a952844ef3f7ebefd8803	2024-09-02T17:11:51+02:00	Xuan Son Nguyen		server : refactor multitask handling (#9274)
8f1d81a0b6f50b9bad72db0b6fcd299ad9ecd48c	a47667cff41f5a198eb791974e0afcc1cddd3229	2024-09-01T22:38:17+08:00	Molly Sophia		llama : support RWKV v6 models (#8980)
7ea8d80d53364f2cdcd7bbc0f031106f529b1fe3	42c76d1358021ccdbe8ba89109c143dd7ae166df	2024-08-30T13:21:57+08:00	tc-mb		llava : the function "clip" should be int (#9237)
9fe94ccac92693d4ae1bc283ff0574e8b3f4e765	66b039a5011522b6a61495eea2a9862601e169f7	2024-08-28T17:28:00+02:00	slaren		docker : build images only once (#9225)
66b039a5011522b6a61495eea2a9862601e169f7	20f1789dfb4e535d64ba2f523c64929e7891f428	2024-08-28T13:20:36+02:00	slaren		docker : update CUDA images (#9213)
3246fe84d78c8ccccd4291132809236ef477e9ea	78eb487bb0038eae95506d3d832b94c979185b09	2024-08-27T20:33:08+08:00	Xie Yanbo		Fix minicpm example directory (#9111)
ad76569f8e78ab6ca921bda25cef25a157361719	7d787ed96c32be18603c158ab0276992cf0dc346	2024-08-26T22:58:50-07:00	arch-btw		common : Update stb_image.h to latest version (#9161)
a1631e53f6763e17da522ba219b030d8932900bd	fc54ef0d1c138133a01933296d50a36a1ab64735	2024-08-21T17:58:11-04:00	compilade		llama : simplify Mamba with advanced batch splits (#8526)
f63f603c879c2232eaeded8c0aeba4244471d720	8455340b874aa90d5f70104c99ed2778d9e31c36	2024-08-21T09:45:49+02:00	fairydreaming		llava : zero-initialize clip_ctx structure fields with aggregate initialization 908)
2f3c1466ff46a2413b0e363a5005c46538186ee6	50addec9a532a6518146ab837a85504850627316	2024-08-21T04:00:00+09:00	Changyeon Kim		llava: Add ACC OP for GPU acceleration to the Vulkan backend in the LLAVA CLIP model. (#8984)
d565bb2fd5a2a58b9924a7a34e77a87c78c52137	ee2984bdaf10c14d440ad873a049bcc09b786d9b	2024-08-16T21:34:41+08:00	tc-mb		llava : support MiniCPM-V-2.6 (#8967)
7c3f55c10051c634546247387c5c359c9d499360	911b437f228e75aa3d235acec21bfddd23ecce2f	2024-08-10T11:43:26+02:00	fairydreaming		Add support for encoder-only T5 models (#8900)
3071c0a5f218f107dabd13b73f6090af683ef5ec	4305b57c80eff4f0df5f6acb60b292f03b8f0dd0	2024-08-09T18:33:53+08:00	tc-mb		llava : support MiniCPM-V-2.5 (#7599)
5b2c04f4925e152c362b824f4b41eb2a081fa623	6f6496bb0999d1bce5daff0cfc55ceb0dd13c888	2024-08-09T08:33:30+02:00	Daniel Bevenius		embedding : add --pooling option to README.md [no ci] (#8934)
daef3ab233fc02e4c53afd9b07366379876f00d1	345a686d8271a24db20d31789c0d4b9ed51dcb0c	2024-08-09T08:32:02+02:00	Mathieu Geli		server : add one level list nesting for embeddings (#8936)
15fa07a5c564d3ed7e7eb64b73272cedb27e73ec	be55695eff44784a141a863f273661a6bce63dfc	2024-08-07T18:24:05+02:00	slaren		make : use C compiler to build metal embed object (#8899)
cdd1889de62a7140c8c016405ec917464bde8bd3	c21a896405de4cdf4207eb8130555ceaac0ab110	2024-08-06T02:20:54-05:00	Douglas Hanley		convert : add support for XLMRoberta embedding models (#8658)
a3738b2fa7c60ef2c4592435d1aa7fb8f1f69c3e	655858ace0cf2720e56eb01f84ad05e0c94ada3c	2024-08-04T17:28:08+02:00	0cc4m		vulkan : implement Stable Diffusion operators (ggml/904)
afbbcf3c04e3c6420cad3d72571478cd62ac176c	ed9d2854c9de4ae1f448334294e61167b04bec2a	2024-07-31T18:59:09-05:00	Igor Okulist		server : update llama-server embedding flag documentation (#8779)
c887d8b01726b11ea03dbcaa9d44fa74422d0076	75af08c475e285888f66556d0f459c533b7deb95	2024-07-30T14:56:51+08:00	zhentaoyu		[SYCL] Add `TIMESTEP_EMBEDDING` OP (#8707)
4c676c85e59ef8f771f3a129e6eb217552139231	e54c35e4fb5777c76316a50671640e6e144c9538	2024-07-28T00:42:05-04:00	compilade		llama : refactor session file management (#8699)
c3ebcfa148e867a68e78fd5c4f0c23e8f84c788b	8a4441ea1a2564578134404f31158c318e9c0bf3	2024-07-12T03:14:12-05:00	Douglas Hanley		server : ensure batches are either all embed or all completion (#8420)
d12f781074b92589a72a36ffabb583933f7b9dc0	bcefa03bc01a41aace2e200ee8e77827d6d39b4f	2024-07-05T02:05:56-05:00	Douglas Hanley		llama : streamline embeddings from "non-embedding" models (#8087)
d7fd29fff16456ce9c3a23fd2d09a66256b05aff	6f63d646c1a06a6e09f721009a2676864ae04e31	2024-07-05T05:14:21+12:00	Icecream95		llama : add OpenELM support (#7359)
807b0c49ff7071094f97ebc3a0a8e2b9e274f503	f8c4c0738d72d2162736edd72dd5db8b269adca1	2024-07-04T15:46:11+02:00	fairydreaming		Inference support for T5 and FLAN-T5 model families (#5763)
26a39bbd6b0bbd66118bb68569f0276d7fe7df6c	38373cfbab5397cc2ab5c3694a3dee12a9e58f45	2024-06-28T15:11:44+02:00	Xuan Son Nguyen		Add MiniCPM, Deepseek V2 chat template + clean up `llama_chat_apply_template_internal` (#8172)
9b31a40c6ddabe552875b811d7127aa039ca9703	c70d117c37cc7876e775d1e2722208a50c52edb3	2024-06-27T01:50:09+02:00	Daniel Bevenius		clip : suppress unused variable warnings (#8105)
ae5d0f4b899ff2842bfca561370c945ad8d4368b	31ec3993f6e050322a249c07af79dbde66ea6ddc	2024-06-26T21:59:28+02:00	slaren		ci : publish new docker images only when the files change (#8142)
3791ad219323389106dc3fd80814eb5bbb7b80de	f702a90e245499283d6de0b287701c723cda2a87	2024-06-25T16:57:35+05:30	HanishKVC		SimpleChat v3.1: Boolean chat request options in Settings UI, cache_prompt (#7950)
8cb508d0d5c024e12692370d85237b45469a004b	646ef4a9cfb6f40236d3b9ef07ac03700b6efcc7	2024-06-24T07:36:11+02:00	slaren		disable publishing the full-rocm docker image (#8083)
646ef4a9cfb6f40236d3b9ef07ac03700b6efcc7	de0d6a68ac99f307fe889c48e21124bc3b7ca29a	2024-06-24T13:30:24+08:00	Yann Follet		embedding : more cli arguments (#7458)
11318d9aa1f668aa10407a5cb9614371af32f3ce	b6b9a8e606da7764bd3649c2ea574979c85abd43	2024-06-23T15:39:45+02:00	Daniel Bevenius		Fix typo in llama_set_embeddings comment (#8077)
80ea089d771f0c2d97afa8bead80ded412f600d7	0e64591e8290037db6412665a56354b789a0597e	2024-06-21T00:38:22-05:00	Douglas Hanley		llama : allow pooled embeddings on any model (#7477)
0c7b3595b9e5ad2355818e259f06b0dc3f0065b3	7b2f4a7d193ef2475259bbe7656fcccfab4b1217	2024-06-15T18:53:40+02:00	Xuan Son Nguyen		Add `cvector-generator` example (#7514)
c2ce6c47e4f2d891bf29d8810832a3b310a8f205	b61eb9644d64e90123ac805436d95b94b3b4cc3f	2024-06-11T07:59:20+02:00	slaren		fix CUDA CI by using a windows-2019 image (#7861)
a5cabd76491f07494c5b8267f921c73f5e2bbfb4	d5c938cd7716b9a2ace49a43a469dfbffcff4d28	2024-06-07T15:09:45+08:00	woodx		server : do not get prompt in infill mode (#7286)
2d08b7fbb483c14bd2b173d4cd51ea3a4f862e8f	d67caea0d6e6c303d31b01d0a010973e6c908dff	2024-06-06T07:19:49+02:00	slaren		docker : build only main and server in their images (#7782)
6f28a333c1e3fdfdc7b4f9d0367f2b41a9b7e9d4	549279d8049d78620a2b081e26edb654f83c3bbd	2024-06-03T15:49:30+08:00	zhangkaihuo		llama : MiniCPM support tied embeddings (#7664)
74b239b3d5f067470d7ef5e26e2e059720572e32	852aafb163d32d5bad63c10bc323a02c28fec59d	2024-05-28T11:48:16+09:00	Ikko Eltociear Ashimine		llava : update clip.h (#7580)
152da28ae54139e3754189b9e6e1c28e11277502	d48c88cbd563b6cf0ce972e2f56796896e240736	2024-05-23T17:40:43+10:00	Brian		labeler.yml: add embedding label detector [no ci] (#7482)
65c58207ece92ad213f4bfd0f91dcb2dfb664f5b	1cc0155d04918cb3017afa472acea51b77483c4a	2024-05-20T15:19:21+08:00	junchao-loongson		ggml : add loongarch lsx and lasx support (#6454)
e932094d58f513d5996c3efc9f6fed8238894c57	2789baf480ba7dc9281b65f601f0918e58920f54	2024-05-20T08:56:05+03:00	Georgi Gerganov		server : return error on too large embedding input (#7389)
33c8d50accd6dca73c9c4af00a05e24209c160fe	d359f30921a9f62a0fd299c412ff3f270286fea6	2024-05-19T19:18:39-07:00	Srihari-mcw		Add provisions for windows support for BF16 code including CMake provision for enabling AVX512_BF16 (#7258)
f030ec1f7a72aa825b2104823946551b9ec5dfc1	e4e6f67be6a8a697f5f89a28c98934e53c99c359	2024-05-19T17:19:53+02:00	0cc4m		Vulkan Embedding Fix (#7360)
ea3b0590ee33d3573eb8ef76f88cc60f36d2a38d	29499bb59383c2a8c5d557a90abb08b696cef7f6	2024-05-15T20:01:12+08:00	dm4		embedding : free the batch after execution (#7297)
27f65d6267cf22a44c5ccefa7765d53a05bd1259	ee52225067622babc277371511b8124884e1c797	2024-05-14T14:20:47+09:00	Ryuei		docs: Fix typo and update description for --embeddings flag (#7026)
b83cc3f5b303ff30c52874b2d5864dc6385ebf9f	9cb317f77e53067f7a138cc89ef7657148eae8e6	2024-05-11T09:46:09+02:00	Joan Fontanals		llama : add Jina Embeddings architecture (#6826)
f89fe2732c5709f6e86d5f4aee2e6d2a561f2eb2	d11afd665241c1b3910ab5f040d0216403019d87	2024-05-10T15:51:58+05:30	HanishKVC		Main+: optionally allow special tokens from user in interactive mode (#7097)
d11afd665241c1b3910ab5f040d0216403019d87	8c570c9496212073079476651c7517c02581101f	2024-05-10T02:41:10-04:00	Andrei		llava : fix moondream support (#7163)
47345248827f426038098d016ed11975021b4919	07cd41d0965829463eff73eda3348aedbfd3a444	2024-05-09T17:34:37+08:00	Albert Jin		opencl : alignment size converted from bits to bytes (#7090)
9da243b36ac0b9d609adfaaa4c8f1cc8c592f737	bd1871fa2b1bf8a081b43ba9bc85f8ffd46fac46	2024-05-08T22:14:39+03:00	Georgi Gerganov		Revert "llava : add support for moondream vision language model (#6899)"
ffe666572f98a686b17a2cd1dbf4c0a982e5ac0a	24affa7db3c9db148854b0ab4fd63de8bca7d898	2024-04-29T07:34:24-07:00	cpumaxx		llava-cli : multiple images (#6969)
3055a4180557c6cbe29eacc8284c9e070ac10eab	577277ffd203b190c3dc2ab3e737946dc432132c	2024-04-29T09:34:41-04:00	Christian Zhou-Zheng		convert : fix conversion of some BERT embedding models (#6937)
46e12c4692a37bdd31a0432fc5153d7d22bc7f72	dba497e0c1eff27cf0e85d1d73c86fa08e1b5557	2024-04-25T12:38:31-07:00	vik		llava : add support for moondream vision language model (#6899)
4ab99d8d4762869506bb675b36501fd7c2af00b2	54770413c484660d021dd51b5dbacab7880b8827	2024-04-25T14:38:14+02:00	Daniel Bevenius		clip : rename lerp function to avoid conflict (#6894)
8cc91dc63c0df397d644a581b2cbeea74eb51ae0	dbceec87c0221ec952e69448df6a71f1372a7487	2024-04-16T14:55:30-04:00	Justine Tunney		ggml : add llamafile sgemm (#6414)
67fac4b95fcccfda8ab965e9ba4992a9ddf3a25f	29122d32ac8075ad27b7a8be05dcad2b7e7a5f9e	2024-04-10T08:58:48+02:00	Pierrick Hymbert		docs : how to add a model (#6565)
1b67731e184e27a465b8c5476061294a4af668ea	c4a3a4ff47d62d2503ddf9bd91b58c21f04fe3c3	2024-04-09T13:44:08-04:00	Jared Van Bortel		BERT tokenizer fixes (#6498)
5dc9dd7152dedc6046b646855585bd070c91e8c8	e11a8999b5690f810c2c99c14347f0834e68c524	2024-04-09T09:16:13+01:00	Carolinabanana		llama : add Command R Plus support (#6491)
e3c337d87ca650972105a51c6ce302dd236c07ad	beea6e1b16e783a0886e78dec01002a8c00db24d	2024-04-08T06:02:30-07:00	Rick G		llama : support negative ith in llama_get_ API (#6519)
22a462cc1f69873f7d4c6d0201bd93478afa2ecb	f6a0f5c6422200764b7929064c39dcf4bb0e9cd6	2024-03-26T16:22:07Z	Someone Serge		nix: package: don't introduce the dependency on python
a016026a3ac16d8c9b993a3573f19b9556d67de4	53c7ec53d5eca26b2c0c648605543a5fa6c12817	2024-03-27T20:26:49+01:00	Pierrick Hymbert		server: continuous performance monitoring and PR comment (#6283)
1e13987fba5a536965ef942f2c86549d62cef50b	e82f9e2b833d88cd2b30123ef57346c2cb8abd99	2024-03-27T12:15:44+01:00	howlger		embedding : show full embedding for single prompt (#6342)
557410b8f06380560155ac7fcb8316d71ddc9837	55c1b2a3bbd470e9e2a3a0618b92cf64a885f806	2024-03-26T10:46:41-04:00	compilade		llama : greatly reduce output buffer memory usage (#6122)
deb7240100da99555b9ab9dc635021e591fceaf5	3d032ece8e6973441273601ca2981130608e287d	2024-03-26T18:11:46+09:00	Minsoo Cheong		embedding : adjust `n_ubatch` value (#6296)
1d0331c12a2f2a6296b471232bd4e66fbf06e6a1	dba1af612926cbd4ebe2d876277af1e3305177e0	2024-03-22T19:47:14+01:00	Kawrakow		quantize: options for output and token embedding tensors qtype (#6239)
272935b281fee5c683e3d6d1eb580b84553cf503	ccf58aa3ec4d20b10162ba40898dc038ad4c3fad	2024-03-20T23:02:32+08:00	Ziang Wu		llava : add MobileVLM_V2 backup (#6175)
f8c4e745e1e728204ab26dbadf52853545e6789c	47cc7a7bf9793f81a6dfe7c2096c499403f64dd6	2024-03-20T19:20:37+08:00	Ziang Wu		llava : add a MobileVLM_V2-1.7B backup (#6152)
104f5e0fc156d48476258295457cafeec2a2af10	5e1b7f94a03e0b3b8e4578625bbdadc7bbd2b93c	2024-03-18T16:40:22+01:00	Felix		clip : fix memory leak (#6138)
877b4d0c628cc70dddb5df72ed8fc14d126ca7e8	12247f4c69a173b9482f68aaa174ec37fc909ccf	2024-03-15T13:43:02-07:00	Theia Vogel		llama : add support for control vectors (#5970)
12247f4c69a173b9482f68aaa174ec37fc909ccf	4e9a7f7f7fb6acbddd1462909c8d696e38edbfcc	2024-03-15T16:41:22-04:00	Andrew Canis		llama : add Command-R support (#6033)
044ec4b2a567f649459ccd20af2f387c784faa51	77178eedc83d49f31bf757d8e12315d76460be78	2024-03-14T15:14:14+02:00	Georgi Gerganov		embedding : add EOS token if not present (#899)
68265ebfc6a1bed022973ea0c3145be1450b7e70	381da2d9f0940d7009e3e918bed36338c8ff2fbb	2024-03-14T12:37:20+02:00	Georgi Gerganov		embedding : print all resulting embeddings (#899)
381da2d9f0940d7009e3e918bed36338c8ff2fbb	0fd6c1f015f6cccf3b527f7dbd8386a434728126	2024-03-14T11:55:23+02:00	Georgi Gerganov		metal : build metallib + fix embed path (#6015)
0fd6c1f015f6cccf3b527f7dbd8386a434728126	19885d205e768579ab090d1e99281cae58c21b54	2024-03-14T10:12:29+02:00	Georgi Gerganov		embedding : print cosine similarity (#899)
f30ea47a87ed4446ad55adb265755dc9102956a2	d8fd0ccf6ac8b07791ffd1575eed436930854ae3	2024-03-13T18:54:21+01:00	slaren		llama : add pipeline parallelism support (#6017)
99b71c068f624521ad977e08e41589e2971fa1c7	306d34be7ad19e768975409fc80791a274ea0230	2024-03-13T11:39:11+01:00	Xuan Son Nguyen		Server: Use multi-task for embeddings endpoint (#6001)
828defefb66fc8a25404f5de845897145bf34061	caa106d4e05a0ab94225c220b81f9e2cd522339b	2024-03-11T14:40:42+01:00	Jakub N		Update server docker image URLs (#5997)
ecab1c75de68de7c41c254e2ae170d3b07bee6d4	ee35600b9061b1ea0c4ea87fce6844297632b2a8	2024-03-11T10:00:08+02:00	Gilad S		cmake : fix subdir for `LLAMA_METAL_EMBED_LIBRARY` (#5985)
bcebd7dbf62fd7b293d5ed089023e4e733269c71	2960eae847f8dbde23be6d170a61bcf44ebf32de	2024-03-10T11:56:30-04:00	DAN™		llama : add support for GritLM (#5959)
fb215c3832236fec7380c4fb618bd7154cb196ef	2c4f566c88322ebf2f9bd11b01b5ebdaa0130b89	2024-03-09T21:27:58+09:00	SeungWon Jeong		server : normalize embeddings (#5956)
950ba1ab84db199f0bbdecdb2bb911f35261b321	e1fa9569ba8ce276bc7801a3cebdcf8b1aa116ea	2024-03-09T11:27:53+01:00	Xuan Son Nguyen		Server: reorganize some http logic (#5939)
c2101a2e909ac7c08976d414e64e96c90ee5fa9e	515f7d0d4fce41c752fc253acf30707c3be2531e	2024-03-08T17:31:00-05:00	compilade		llama : support Mamba Selective State Space Models (#5328)
e457fb3540e0aaec47cfde0abf784c213f9216ee	af37fd8b30e37ccbffdd82e6f48559e2fb7ce7dd	2024-03-08T02:41:50-08:00	Don Mahurin		llama : assume tied weights if lm_head/output weights is missing (#5824)
6cdabe652695167263c8b447520987b11856f7ca	89fb735fcfd21781a8194b211cf32824beb3f71f	2024-03-07T16:32:38+02:00	Georgi Gerganov		llama-bench : add embeddings option (#5924)
2002bc96bf2cbf5ab981a17d7e994d817c9801f5	ceca1aef0738b57951cd12c603c3477e75312dec	2024-03-07T11:41:53+02:00	Georgi Gerganov		server : refactor (#5882)
21b08674331e1ea1b599f17c5ca91f0ed173be31	6a87ac3a52668e117d97bcea07b529c93188b303	2024-03-05T16:08:35+08:00	Neo Zhang Jianyu		[SYCL] fix mul_mat fault in CI/unit-test (#5862)
29ae62d2ae163e2b68aa0ad3bf2ab4636de0c957	e0843afe1b37890b631bc7d3d2da2ed36c862b91	2024-03-04T22:31:20+02:00	Georgi Gerganov		llama : fix embeddings (#5796)
7d43c585dc174bb586775c22c15e5db9242b5b4b	82f3e668adafba647de703f835991e91a96b5ac4	2024-03-03T20:23:52+08:00	leejet		add some new ops, fix some operators and add batch operations to certain operators. (ggml/747)
475df1d6cf817060028d3ff763cb8097d4ec40d6	87c2e8b2797860a06af3d6c06b8488a8ff1a09ab	2024-03-03T04:40:27-06:00	Douglas Hanley		llama : allow for user specified embedding pooling type (#5849)
c29af7e2252d288f2ea58a7d437c1cb7c0abf160	38d16b142624bdd7c41d9955752b7f7b59c5e048	2024-03-02T01:00:46+05:30	Sourab Mangrulkar		llama : add StarCoder2 support (#5795)
9e359a4f47c1b2dceb99e29706c9f7403d32ab5e	4c4cb30736582cacb1a164a9d4bc8e17b1014be7	2024-02-24T19:16:04+01:00	Pierrick Hymbert		server: continue to update other slots on embedding concurrent request (#5699)
525213d2f5da1eaf4b922b6b792cb52b2c613368	fd43d66f46ee3b5345fb8a74a252d86ccd34a409	2024-02-24T12:28:55+01:00	Pierrick Hymbert		server: init functional tests (#5566)
201294ae177b308fb3a99dc504dd6d27e8afa907	5a9e2f60ba3d8362ba17c77ac3092906d49b813f	2024-02-22T19:44:10Z	Someone		nix: init singularity and docker images (#5056)
580111d42b3b6ad0a390bfb267d6e3077506eb31	88c46cbdac05cebd936511b1d3c74112e721615f	2024-02-21T05:08:22-08:00	postmasters		llama : add `gemma` model (#5631)
6560bed3f066c876682464762cad90f1e28e3f1b	06bf2cf8c406e6b70dbf9b431a02fa0ad845b9df	2024-02-20T11:07:22-08:00	CJ Pais		server : support llava 1.6 (#5553)
8dbbd75754d43ec7b4bbe42fb287cc2553fdf0e9	c0a8c6db371cb3e4379900867b948879f5842201	2024-02-19T22:58:36-11:00	Haoxiang Fei		metal : add build system support for embedded metal library (#5604)
890559ab28e354052e16e770155ad007fd0856e8	d0e3ce51f45bd6a646da1952d7e5d143a087db3e	2024-02-11T16:41:41+02:00	Didzis Gosko		metal : option to embed MSL source into compiled binary (whisper/1842)
60ed04cf82dc91ade725dd7ad53f0ee81f76eccf	594845aab1c6775877f6d9545a51dc0f8d0b3d77	2024-02-16T10:24:39+01:00	Daniel Bevenius		llava : fix clip-model-is-vision flag in README.md (#5509)
4524290e87b8e107cc2b56e1251751546f4b9051	c06e45d72983d9ace7b1535f7e7ea258d212169e	2024-02-15T11:21:49-06:00	Douglas Hanley		Use correct type of pooling for embedding models (#5500)
c06e45d72983d9ace7b1535f7e7ea258d212169e	9060a1e9dfca6038906e819be5fa42217f49028c	2024-02-15T18:49:08+02:00	Georgi Gerganov		clip : fix wrong loop condition
0d4177126b0556e202efb85bf3f768be81076400	7930a8a6e89a04c77c51e3ae5dc1cd8e845b6b8f	2024-02-15T09:01:57+01:00	Elbios		llava : fix memory management bug (#5491)
7930a8a6e89a04c77c51e3ae5dc1cd8e845b6b8f	704359e29985a06a389337a2617b7f3fa8eff908	2024-02-15T08:59:18+01:00	John		llaba : hotfix for llava-1.6 image number (#5495)
aa2341298924ac89778252015efcb792f2df1e20	f5ca054855dea83f424003162f26de376e5643f6	2024-02-14T08:38:35+01:00	John		llava : support v1.6 (#5267)
ea9c8e11436ad50719987fa23a289c74b7b40d40	c4e6dd59e45ef7b14f7763fb073b517395dc176c	2024-02-13T12:03:53-05:00	Jared Van Bortel		llama : add support for Nomic Embed (#5468)
03bf161eb6dea6400ee49c6dc6b69bdcfa9fd3fc	ad014bba97ef6ef6c3e2f78b2fc463e91ae94579	2024-02-13T06:06:58-06:00	Douglas Hanley		llama : support batched embeddings (#5466)
4a46d2b7923be83d6019251671ee63aa1fa0d6bc	3b169441dfe8e420f88d1592708cc2a871daadb9	2024-02-12T09:38:44+01:00	Daniel Bevenius		llava : remove prog parameter from ArgumentParser (#5457)
3b169441dfe8e420f88d1592708cc2a871daadb9	3bdc4cd0f595a6096cca4a64aa75ffa8a3503465	2024-02-12T09:16:06+02:00	Georgi Gerganov		sync : ggml (#5452)
2891c8aa9af17f4ff636ff3868bc34ff72b56e25	97a336507ed9b971d72262bec7e2b8b7016a054a	2024-02-11T10:21:38-06:00	Douglas Hanley		Add support for BERT embedding models (#5423)
ff4ff05c5ff4311c05a8ce1f984c7d8def4f07a5	b7b74cef36a93ae01e0b9af8986d131761742d0e	2024-02-08T15:20:03+01:00	Daniel Bevenius		llava : add missing .py, and fix paths in README.md (#5414)
4aa43fab569215a13495a7f1a0f8afc541b16d03	a6e514a85f0fda38ff78ec91782877ea3d19ed98	2024-02-08T18:36:19+08:00	runfuture		llama : fix MiniCPM (#5392)
a6e514a85f0fda38ff78ec91782877ea3d19ed98	26d4efd11e48908e14e2ee9471a7fc4c57079a1d	2024-02-08T09:58:19+01:00	Daniel Bevenius		llava: fix typo/formatting in README.md (#5405)
316c7faf7740fa98ea68f1445f4505810f706b9e	f3e2b4fa3f81a410ecb7dec929c259ef8d8dbb7d	2024-02-07T14:15:56+08:00	runfuture		llama : add MiniCPM support (#5346)
6b91b1e0a92ac2e4e269eec6361ca53a61ced6c6	e805f0fa9951081ce0a86378a7aa52b6f636b82d	2024-02-02T08:56:31+01:00	Xuan Son Nguyen		docker : add build for SYCL, Vulkan + update readme (#5228)
c82d18e863fcde91b4b1109b1d0c73ea4470c405	14fef85e2d5361e6b4dd7a9ecf22bb817362997d	2024-01-29T21:48:10+08:00	Wu Jian Ping		server : embeddings compatibility for OpenAI (#5190)
39baaf55a160909bb9428bd981014218761a20cb	6db2b41a76ee78d5efdd5c3cddd5d7ad3f646855	2024-01-28T01:55:31-06:00	Kyle Mistele		docker : add server-first container images (#5157)
6db2b41a76ee78d5efdd5c3cddd5d7ad3f646855	753eafed0ebd07af6903771327a1786a7c02cf98	2024-01-27T16:09:18+01:00	John		llava : support for Yi-VL and fix for mobileVLM (#5093)
bf63d695b804b1c995c7ae4427a8a86936ea6d25	1387ea21178f9f154944013d4dd9764b54c69deb	2024-01-22T03:17:05-07:00	Michael Hueschen		nix: add cc to devShell LD_LIBRARY_PATH
57e2a7a52a819883f40dada8a2edc24ecf48186b	9b6ea4263ab45e02ff905bf7a29dc143ca1facc3	2024-01-18T23:12:15+01:00	John		llama : fix falcon arch for tied output embeddings (#4978)
ee8243adaa9a9f51ff449213383874e49efe368f	15ebe59210e7fd9817ff67f51fa1a5ee2d004294	2024-01-13T14:16:11Z	makomk		server : fix crash with multimodal models without BOS token (#4904)
d34633d8db6c2e400355de4862cd699154ecc73f	4f56458d34cb13dcbf69aca650e9bf77d5497e6f	2024-01-10T14:37:09+01:00	John		clip : support more quantization types (#4846)
36e5a08b203542dca53cca4eaf172c5dc4bbc991	4dccb38d9abab7f9f2d1f9a6977df4185d490132	2024-01-09T09:59:14-08:00	Justine Tunney		llava-cli : don't crash if --image flag is invalid (#4835)
3418c03ecc149fd657527ebb06776239b60a3f3b	63ee677efd92060b14894b984597c62e3742b8da	2024-01-07T08:46:55+01:00	Alex Azarov		llama.swiftui : add visionOS target (#4805)
9fbda719de18a9400a064c28759c39d55d687d3e	39d8bc71edcb8b6f99d46fa4216af7a15232e218	2023-12-30T23:24:42+02:00	Georgi Gerganov		clip : refactor + bug fixes (#4696)
0235b9b571f3cc7d2b8836409a5404b41ce1379c	ce18d727a47f2473ca863a6f78bf3ad480008f72	2023-12-29T18:53:34+02:00	Georgi Gerganov		clip : use ggml_backend_buffer_is_host (#4205)
ce18d727a47f2473ca863a6f78bf3ad480008f72	91bb39cec7e4dfb9e2293509ef60298a67f0b1b7	2023-12-29T11:52:15-05:00	Steward Garcia		clip : enable gpu backend (#4205)
b93edd22f55d3e5268263c3edcdae1818505c078	82d6eab224862a7044069fb9211dc4b29124264b	2023-12-29T06:22:10-08:00	Karthik Sethuraman		server : allow to generate multimodal embeddings (#4681)
925e5584a058afb612f9c20bc472c130f5d0f891	6123979952385847d8348e295d77d6e01da8aa84	2023-12-23T11:35:55+02:00	Samuel Maynard		ci(docker): fix tags in "Build and push docker image (tagged)" (#4603)
f31b98489824a86c937fa62ccf5dfd4bb0327b86	2bb98279c5a087d62949972b35cf63ff974ffe6a	2023-12-21T23:56:34-07:00	rhuddleston		ci : tag docker image with build number (#4584)
33c9892af58b7b161f2a532935dcccff8c8048c6	8efa0f6ebed53c9453e6721da86fb294e5015909	2023-11-30T23:11:14+01:00	John		llava : ShareGPT4V compatibility (vision encoder only loading) (#4172)
bd90eca237b498dd106d315dcb9ad3e6fae3906f	3d68f364f15778dc326f5024f2e5af1ad6dfddef	2023-11-13T18:20:52+03:00	M. Yusuf Sarıgöz		llava : fix regression for square images in #3613 (#4056)
381efbf480959bb6d1e247a8b0c2328f22e350f8	2833a6f63c1b87c7f4ac574bcf7a15a2f3bf3ede	2023-11-06T22:36:23+01:00	Damian Stewart		llava : expose as a shared library for downstream projects (#3613)
ca190bca8e844d171020d6147687e71472d71734	71e3718abdb2771b50c9606d3a7569623a0b0afe	2023-11-01T09:28:28Z	Adrian Hesketh		server : re-enable completion and embedded at the same time (#3876)
34b2a5e1ee4fe6295fb4420eb91131d743694c65	6961c4bd0b5176e10ab03b35394f1e9eab761792	2023-10-26T22:53:37+03:00	Georgi Gerganov		server : do not release slot on image input (#3798)
438c2ca83045a00ef244093d27e9ed41a8cb4ea9	9e70cc03229df19ca2d28ce23cc817198f897278	2023-10-22T22:53:08+03:00	Georgi Gerganov		server : parallel decoding and multimodal (#3677)
f3b25e40438b3c8383caabf4e7b89863145a9f0e	60abea9798f47b918a9f38c66edfd88c526d20f6	2023-10-19T19:40:41+03:00	M. Yusuf Sarıgöz		multimodal : add BakLLaVA conversion support (#3682)
cb33f43a2a9f5a5a5f8d290dd97c625d9ba97a2f	e1675d133c31e1c8de2f06be7164e12c0ba6cf2c	2023-10-17T22:24:50+02:00	slaren		fix embeddings when using CUDA (#3657)
940efa95fec0b8a98c226a889d2ad839dfeeae0d	11bff290458f12f020b588792707f76ec658a27a	2023-10-16T23:58:00+03:00	Georgi Gerganov		llava : fix tokenization to not add bos between image embeddings and user prompt (#3645)
370359e5baf619f3a8d461023143d1494b1e8fde	9e24cc6e2e589d405bd1720c400f5b0b9d0ca3ee	2023-10-12T18:23:18+03:00	M. Yusuf Sarıgöz		examples: support LLaVA v1.5 (multimodal model) (#3436)
f5f9121de140eff558f13b5c5e78a3a3b6b94377	11ea5c7d96f2c28e1c99659e08ec0a44574056e2	2023-10-10T09:50:23+02:00	Jan Ploski		llm : add MPT support (#3417)
a8777ad84e00cda0399e827cdf971e2c3fab1da2	97af49fa395df77e4c18af0e1655b2fee67c9686	2023-10-06T14:16:38+01:00	pudepiedj		parallel : add option to load external prompt file (#3416)
0e76a8992c8200237bbc6471a53fb8796b3872f7	2db94d98eda56982d80238840b0652b4137a2a84	2023-09-28T20:40:11+02:00	xaedes		train : finetune LORA (#2632)
f56c418ab0a635c020bcb5bf44b8f00cb3c9e514	8185710a80531e9ee0c0cb99d3a9c9af1019ab67	2023-09-21T17:57:40+09:00	yuiseki		embedding : update README.md (#3224)
4fe09dfe665c58a753dc9eb638dd4dca1cd35488	80291a1d02a07f7f66666fb576c5b1e75aa48b46	2023-09-16T03:02:13+08:00	Meng Zhang		llama : add support for StarCoder model architectures (#3187)
980ab41afba96106cd29cdf3aa6f948c251cb71f	e394084166baac09e8ee9a08a4686f907f7e5291	2023-09-14T09:47:00-07:00	dylan		docker : add gpu image CI builds (#3103)
71d6975559acfd6c8407a4ef8275a9979c737765	b532a69b2fd08067f34f32f37a2fd9b37678a34a	2023-08-30T19:14:53+03:00	Henri Vasserman		[Docker] fix tools.sh argument passing. (#2884)
44c117f41ee01c5ac8fb86bba041f08d8b87b46d	43033b7bb4858da4f591715b3babdf906c9b7cbc	2023-08-28T21:51:47+02:00	xaedes		train : mem usage and other improvements  (#2439)
c82742ac9cd96fd34aa961978805c1d8a361d589	28b2c996ca0ab90a5669946084f13443ec98e241	2023-08-25T11:18:48-04:00	Matt Pulver		llama : add llama_beam_search() (#2267)
3f460a2b723c8b936ac29ecfd02f244b3adeba55	87e3733f24a85d894cc16e1cbdfa1ea1e81a76f3	2023-08-25T11:55:59+03:00	Georgi Gerganov		cuda : add RoPE kernel for mode == 2 (NeoX) (#2760)
95385241a91a616788a3bb76d12c9b7b2379ca2d	335acd2ffd7b04501c6d8773ab9fcee6e7bf8639	2023-08-23T20:33:05+01:00	Olivier Chafik		examples : restore the functionality to import llama2.c models (#2685)
bac66994cf356cf488078c056831396eb4ce31d5	519c981f8b65ee6c87c2965539685ced0a17223b	2023-08-22T19:14:09+03:00	Kawrakow		Quantization imrovements for k_quants (#2707)
519c981f8b65ee6c87c2965539685ced0a17223b	1123f7fbdfb8012e46f05e903e6f675922916378	2023-08-22T16:03:12+02:00	slaren		embedding : evaluate prompt in batches (#2713)
bbef28218fe827265716b66977719b9ee2b21165	5656d10599bd756dc0f17284e418e704200b43f3	2023-07-11T22:01:08+08:00	LostRuins		Possible solution to allow K-quants on models with n_vocab!=32000 (#2148)
7f0e9a775ecc4c6ade271c217f63d6dc93e79eaa	b472f3fca558b6335adbd87210ed58cfb5da37cb	2023-07-04T18:33:33-05:00	Nigel Bosch		embd-input: Fix input embedding example unsigned int seed (#2105)
7ee76e45afae7f9a7a53e93393accfb5b36684e1	acc111caf93fc6681450924df9f99679c384c59e	2023-07-04T10:05:27-04:00	Tobias Lütke		Simple webchat for server (#1998)
698efad5fbbf326f01288649b123eff5f79b417e	14a2cc71f62e45803ae70890ffbdeb0a172e6210	2023-07-04T01:50:12+02:00	Erik Scholz		CI: make the brew update temporarily optional. (#2092)
cfa0750bc9dbc2d957a91b8ed09ab0035d8f3d4e	9d23589d638dc74577d5ff880e6d4248b795f12e	2023-06-28T23:53:37+08:00	ningshanwutuobang		llama : support input embeddings directly  (#1910)
20568fe60f00155fa25e92eb3a7f6b911d557967	18b35625c3c19c64b7818a12460ba5ddb006dfdc	2023-06-20T01:12:39+03:00	Henri Vasserman		[Fix] Reenable server embedding endpoint (#1937)
ca7c3f4da5d144d4cd1dd44903552e6ba49b8ec8	b97ca431db35ec96a339a721acb1219c1dd78bed	2023-06-19T18:14:09+03:00	Kawrakow		cuda : faster k-quants on older GPUs (#1930)
794db3e7b982fee37e3995db9c3a216a57ff65e3	5ddf7ea1fb42bac21026de2f77e0f9c069b92234	2023-06-17T07:53:04-04:00	Randall Fitzgerald		Server Example Refactor and Improvements (#1570)
e32089b2c20b1b87b22912f4a8b93fe01647d5b9	2347e45e7bdb09c9a7d74b2c0bc86c2b65f0c343	2023-06-13T21:04:40+02:00	xaedes		train : improved training-from-scratch example (#1652)
0e730dd23b0fb5f93dba574e0a48d9a69dc5dbae	3b126f654fceb4f5f195a1c2e825bb18e101188c	2023-05-29T06:45:50+02:00	Jiří Podivín		Adding git in container package dependencies (#1621)
6456a4eb9f9c1f4de8f6908ef100daa78802ad00	cdd5350892b1d4e521e930c77341f858fcfcd433	2023-05-13T15:24:20+08:00	Rinne		embedding : remove unused code (#1426)
b6e7f9b09e9c340ec97a2fae61c1eb8db861f2f9	50cb666b8a2e35a49b08c0f6bc81138c8f6f2ac1	2023-04-22T08:21:32+02:00	xaedes		llama : add api for getting/setting the complete state: rng, logits, embedding and kv_cache (#1105)
a0c05164168297c04737936ad0cad849a512547a	d8d4e865cd481b18f10508ffee35db903767ef5c	2023-04-02T15:13:03-07:00	bsilvereagle		Remove torch GPU dependencies from the Docker.full image (#665)
e0670260fb50a882b37074112b1881fb0820cf77	28ba975aea1dcae2f31770516f5d542ff177771e	2023-03-28T18:34:35+03:00	Georgi Gerganov		gitignore : add "embedding"
4b8efff0e3945090379aa2f897ff125c8f9cdbae	7e5395575a3360598f2565c73c8a2ec0c0abbdb8	2023-03-28T08:11:09+02:00	RJ Adriaansen		Add embedding example to Makefile (#540)
03f7e335604b3d68f74995aa2ccb4955833ee423	55ad42af845127bd0eb0c1f36f327ecec83f4bca	2023-03-25T20:51:14+02:00	Georgi Gerganov		Cleanup STL headers + fix embedding examples + minor stuff
a316a425d04027453dc0fd45f003b647c12f66f9	ecbe466a364876927994e2f1ec14f4d82301d201	2023-03-25T20:26:40+02:00	Georgi Gerganov		Overhaul the examples structure
8d4a855c241ecb0f3ddc03447fe56002ebf27a37	b6b268d4415fd3b3e53f22b6619b724d4928f713	2023-03-24T08:05:13-07:00	Luciano		Add embedding mode with arg flag. Currently working (#282)
16ffc013c62f22bdaa3cdc022d7a13fd952d73fc	486ae645fd3eda8b9d7413d5ff34fb65a3e337fb	2023-03-21T09:42:25-07:00	comex		Importer for GPTQ quantized LLaMA models (#301)
0f1b21cb90ac6b84a9af70cafb8e13b5389e3b32	074bea2eb1f1349a0118239c4152914aecaa1be4	2023-03-20T18:05:20+01:00	Bernat Vadell		Docker - Fix publish docker image in GitHub Registry (#235)
5cb63e2493c49bc2c3b9b355696e8dc26cdd0380	da5303c1ea68aa19db829c634f1e10d08d409680	2023-03-20T08:24:11Z	Stephan Walter		Add tqdm to Python requirements (#293)
2af23d30434a677c6416812eea52ccc0af65119c	904d2a8d6acd667c9633138d45a361d40fbf76d0	2023-03-17T10:47:06+01:00	Bernat Vadell		🚀 Dockerize llamacpp (#132)