5.5 KiB
5.5 KiB
| 1 | d1bc743c10080fed1253686ce01749b42611ded4 | 2f201160b1960fd7be18b70d5770599d7082dd2f | 2026-05-28T14:23:06+08:00 | wangbomeng | set u_batch = max_seq_len | ||
|---|---|---|---|---|---|---|---|
| 2 | 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 | ||
| 3 | 1921024604db640f09ade83c8a437ebf15bde360 | d028722a12c5a463cc97207787cfd03d7a2590b0 5af229fe518ee2d761ab8ae2a69f7a9aaa9057f4 | 2026-05-21T14:08:14+08:00 | Bomeng Wang | refs/stash | WIP on dev: d028722a replace cparam.n_ubatch with n_ubatch() | |
| 4 | 5af229fe518ee2d761ab8ae2a69f7a9aaa9057f4 | d028722a12c5a463cc97207787cfd03d7a2590b0 | 2026-05-21T14:08:14+08:00 | Bomeng Wang | index on dev: d028722a replace cparam.n_ubatch with n_ubatch() | ||
| 5 | d028722a12c5a463cc97207787cfd03d7a2590b0 | 63442fde8dc285817f725bd6c5fae80f478a3813 | 2026-05-20T14:41:05+08:00 | wangbomeng | replace cparam.n_ubatch with n_ubatch() | ||
| 6 | 63442fde8dc285817f725bd6c5fae80f478a3813 | fc3f4a9fab88e98eff8eeca8cbc6617333edba2c | 2026-05-20T11:47:42+08:00 | wangbomeng | fix ubatch and cmakelist | ||
| 7 | 2716130010c58f1cdd9d94f0e2f8e047bc92dc66 | b35bda124ccd4ed581dd6088d3ffa4931c2809b6 | 2026-05-18T08:40:54+08:00 | Yunzhe Jia | fix n_ctx_slot error by adding runtime capacity loading for cal-llm | ||
| 8 | 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. | ||
| 9 | 5d219bfcef239c1e3ddd1baecc0514a9462ff6a8 | 6787a53ab9b4897c5a7b51a4062d7b90e6697d35 | 2026-04-24T09:31:32+08:00 | wangbomeng | calrt: recover base = batch_index * dict_len | ||
| 10 | d8b2aaa00049978cebac15041f960d75b552f97b | b6f29ec8140028619efaa50aa6e73146cecf631d | 2026-04-13T11:23:44+08:00 | wangbomeng | server: fix context-shift | ||
| 11 | b6f29ec8140028619efaa50aa6e73146cecf631d | 6d55eae7e76b768acfcec045b8e84cded8ae3b55 | 2026-04-13T11:23:31+08:00 | wangbomeng | server: fix context-shift | ||
| 12 | 42a181674565411efa5c8b318bc77d6fd084df8a | bd3a57a11aa008e0b5dc2a30f82fcd3a02587208 | 2026-04-10T09:06:55+08:00 | Yunzhe Jia | fix prompt_cache issue | ||
| 13 | 99d2078e89305035d87d966cee7987c7d50b3925 | 9626239f5a9e568c9975d67dd6745fef90279a87 | 2026-04-08T19:01:16+08:00 | Yunzhe Jia | fix buffer resize problem | ||
| 14 | 4e194ecc6c4b8ebe4c72d93f6055e3605dbfcefa | 16cbf81a731f5839a2f6b0eb9d8539826353748b | 2026-03-24T01:59:03+08:00 | wangbomeng | calrt: fix ubatch.embd cpy | ||
| 15 | 07817cefc14fa359dcecad0630defd3610f8f5c8 | b2c45d8ddefb7ec09435231c8ec5b736fabf9c91 | 2026-03-10T16:32:07+08:00 | Yunzhe Jia | fix kv issue | ||
| 16 | 7ddafbdcb9426ae3af016925b8b596f11e8742d0 | 059009eeaf20a569abfbac5eb37dad3bb9376428 | 2026-03-10T07:13:04+08:00 | wangbomeng | calrt: commented out cal_ctx->encode(batch) | ||
| 17 | b2c45d8ddefb7ec09435231c8ec5b736fabf9c91 | c6ea3f0d2468e3b8eab5de80bacee7fe4c9dd3d7 | 2026-03-09T15:03:26+08:00 | Bomeng Wang | clart: past_kv_len = n_tokens | ||
| 18 | 7a3a9a0e76bb5f530beafcfe52e87e388e93117a | 583c387efaf7bc030574e554088de79d09a27fbd | 2026-03-05T07:24:59+08:00 | wangbomeng | calrt_infer: fix past_kv_len | ||
| 19 | 583c387efaf7bc030574e554088de79d09a27fbd | 0edc14a60a2d5596f71d728c655e3523da924d89 | 2026-02-27T02:24:56+08:00 | wangbomeng | caserver: lim generated tokens to n_ctx_per_seq | ||
| 20 | 0edc14a60a2d5596f71d728c655e3523da924d89 | aa0a17d719326a63e0d6fea60aa0ced44e7abc33 | 2026-02-27T01:57:39+08:00 | wangbomeng | caserver: limit generated tokens to n_ctx_per_seq | ||
| 21 | 365eb0b719e30b0f9e348d854f11c9c3f954a96e | 886cd1fb3b217efcf51c46209fcb694022346797 | 2026-02-07T09:05:17+08:00 | Yunzhe Jia | comment out pos buffer file | ||
| 22 | 6b1ecdbbe3cc72ed8888be38f9e934cfd79b9fbb | 240d9bb75241c91896afe125f2fc74698a7395f3 | 2025-11-25T17:06:14+08:00 | Yunzhe Jia | add kv_tensor for pld test | ||
| 23 | d81d7b190ff5f21325167936496dfe5ab48b922e | e492f5dc8cec17529f53ef2bbdf7b502107f8148 1f5accb8d0056e6099cd5b772b1cb787dd590a13 | 2025-11-04T14:43:32+08:00 | Yunzhe Jia | Merge branch 'master' into dev | ||
| 24 | c20c0a5c0c44179f5267a262546624854b1203d1 | 62425b3a7e8b169a3bbe6ce8c7324513a7fcee8c | 2025-10-20T14:41:08+08:00 | Yunzhe Jia | kv: turn on common-prefix mtmd: fix output size bug | ||
| 25 | 62425b3a7e8b169a3bbe6ce8c7324513a7fcee8c | 76a63a2998286c1649de2496bccb7d8a46549895 | 2025-10-16T17:34:39+08:00 | Yunzhe Jia | kv: let seq_rm free whole seq since current hw-op cannot support common-prefix | ||
| 26 | 76a63a2998286c1649de2496bccb7d8a46549895 | b67217078aa748b06e1b2269d88dd18c0aca2c26 | 2025-10-16T16:31:15+08:00 | Yunzhe Jia | kv: fix common-prefix bug by implementing llama_memory_seq_rm | ||
| 27 | 0115cfb7c1dec0753aecb34f3af4338bf9de8eeb | 3a617cb18121a85eed17ac5585788810c5d9c1e0 0d5a470223fc90b6b6807921d68011ff06ae7f9e | 2025-08-26T15:19:56+08:00 | Yunzhe Jia | Merge branch 'master' into dev | ||
| 28 | 1cbf442f50a154aac0bf35d7b8b3436a2cdfd6f5 | ba67d6c03fed3193987a4ef13050e6e2a4451df4 | 2025-07-24T15:50:19+08:00 | Yunzhe Jia | 1.sync with calrt prefill,decode,kv_update op 2.add hw pattern untile function | ||
| 29 | ba67d6c03fed3193987a4ef13050e6e2a4451df4 | 8f52c6f8abb2ed9ad967cc0bfb90acb073011193 | 2025-06-26T17:42:32+08:00 | Yunzhe Jia | llama-calrt: | infer-op: copy data from output buffer to dst-tensor.data | |
| 30 | 8f52c6f8abb2ed9ad967cc0bfb90acb073011193 | d2f325130c4ed77a3dcff2c23a926587fb08e2cc | 2025-06-26T15:10:45+08:00 | Yunzhe Jia | Squashed commit of the following: | ||
| 31 | d2f325130c4ed77a3dcff2c23a926587fb08e2cc | 6391ee7ffd97e723dfbdcc32f001e1b95a63cba6 | 2025-06-17T11:53:33+08:00 | Yunzhe Jia | calrt: add input_token in graph; input_token will be copy to calrt_in_buffer |