Files

4.2 KiB

1f131bf1908b8c5dd1f49d7ae7f616506fc47166633d96dae28e17208ef61a71dba40cda3c04f135a2026-05-27T09:38:51+08:00wangbomengfix patch of qwen2.5vl,n_patch of minicpm = 64,fix n_ctx_slot,comment out M-ROPE
238ca6895815671a87ceec86b4aa4eb976580ce76ddd60c928224b52eb4e1e60e01e8a1ecbb80ee452026-05-20T16:37:13+08:00Yunzhe JiaAdd support for cal-llm profile dumping to JSONL file
32716130010c58f1cdd9d94f0e2f8e047bc92dc66b35bda124ccd4ed581dd6088d3ffa4931c2809b62026-05-18T08:40:54+08:00Yunzhe Jiafix n_ctx_slot error by adding runtime capacity loading for cal-llm
43b14ed556c15529fe1f94b649f49db7156dfaf67dde8b8228081769c8d8f1e0751d47fa7875f84232026-05-14T14:34:25+08:00Yunzhe 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.
599dd308adb8488fa869bb669e3335e646a938eff06c7852e99e34c71e24e3ef6001cb54c72970e4d2026-04-21T15:50:01+08:00wangbomengtag: v0.2.1server: fix max_seq_len
6ed62eb33447f993d578e156a3c7e38c91b420ece015e988a271573a7c11e2a4b45084e1219d69d502026-04-21T15:05:22+08:00wangbomengtry server-test:not success
7d8b2aaa00049978cebac15041f960d75b552f97bb6f29ec8140028619efaa50aa6e73146cecf631d2026-04-13T11:23:44+08:00wangbomengserver: fix context-shift
8b6f29ec8140028619efaa50aa6e73146cecf631d6d55eae7e76b768acfcec045b8e84cded8ae3b552026-04-13T11:23:31+08:00wangbomengserver: fix context-shift
9a2d5bf362d6c9a546f9deadf4f8975605a915d33bd3a57a11aa008e0b5dc2a30f82fcd3a025872082026-04-09T21:01:46+08:00Bomeng Wangserver: comment fixed time
10b8153b6b8f244b223c9f4c2940ae1f212634519e82842cfc3fa3d5c004c4540aeff8a81f38509bee2026-04-09T15:07:02+08:00wangbomengserver: fix limit tokens to max_seq_len
1182842cfc3fa3d5c004c4540aeff8a81f38509bee622a22991089c6debd5f4b57738f3df3a0bda8b52026-04-09T15:06:26+08:00wangbomengserver: fix limit tokens to max_seq_len
12622a22991089c6debd5f4b57738f3df3a0bda8b55f47a738ba56a37d0ff281a16212f41979568e352026-04-09T10:36:31+08:00wangbomengserver: comment circle print
13ecf01a17651cd7b1e8b85fd6075e83831463ee2399d2078e89305035d87d966cee7987c7d50b39252026-04-09T09:47:55+08:00Yunzhe Jiafix n_parallel problem
1418814f9bf1a423ebe8f32d6043c9cbc5b21b0218bbee06d6d851e3f84f75b578047967d7e0e4a8dc2026-04-08T13:55:52+08:00wangbomengserver : reset inference time
15398ecf71f5f574037ce33f84dd1576fa164909ad6d5e83902bdd3142a8ff0d3db19f02a8619e95a02026-03-27T02:01:23+08:00wangbomengrm llama-server_old.cpp
166d5e83902bdd3142a8ff0d3db19f02a8619e95a0e4eaab700333490e80ebefc8d023f6c1adfcc3122026-03-27T00:57:11+08:00wangbomengserver: printf calrt commit ID
1741e6636ea1fb3884e41fb2023f92b0e7262ef09bd0a1b2c758440720d42fa108b3444f54593daa732026-03-12T16:36:07+08:00Bomeng Wangtag: v0.0.1server: correct the max_seq_len judgment
18583c387efaf7bc030574e554088de79d09a27fbd0edc14a60a2d5596f71d728c655e3523da924d892026-02-27T02:24:56+08:00wangbomengcaserver: lim generated tokens to n_ctx_per_seq
190edc14a60a2d5596f71d728c655e3523da924d89aa0a17d719326a63e0d6fea60aa0ced44e7abc332026-02-27T01:57:39+08:00wangbomengcaserver: limit generated tokens to n_ctx_per_seq
20d81d7b190ff5f21325167936496dfe5ab48b922ee492f5dc8cec17529f53ef2bbdf7b502107f8148 1f5accb8d0056e6099cd5b772b1cb787dd590a132025-11-04T14:43:32+08:00Yunzhe JiaMerge branch 'master' into dev
2198c8269abefdfa8fde47dfb2769ceebc8b704e862790ecc304e384d9075c55d0628d8bf440025dc42025-09-30T17:42:57+08:00Yunzhe Jiaserver: adapt to calrt
22dcbe998a6d8f13b6c9cb36bbe7b355ced2ac384287932ec016f0ec81e98a13ce5212851f8c12458a2025-09-05T14:34:07+08:00Yunzhe Jiaadd calrt API used in server side
230115cfb7c1dec0753aecb34f3af4338bf9de8eeb3a617cb18121a85eed17ac5585788810c5d9c1e0 0d5a470223fc90b6b6807921d68011ff06ae7f9e2025-08-26T15:19:56+08:00Yunzhe JiaMerge branch 'master' into dev
248f52c6f8abb2ed9ad967cc0bfb90acb073011193d2f325130c4ed77a3dcff2c23a926587fb08e2cc2025-06-26T15:10:45+08:00Yunzhe JiaSquashed commit of the following: