Commit Graph

  • d7811a4f32 Merge pull request #1211 from kvcache-ai/support-amx-qwen v0.3 wang jiahao 2025-04-29 06:44:48 +08:00
  • a3ba63665a update readme qiyuxinlin 2025-04-28 22:38:41 +00:00
  • 89823ccb1f update readme qiyuxinlin 2025-04-28 22:34:47 +00:00
  • e7763a4b59 update readme qiyuxinlin 2025-04-28 22:32:35 +00:00
  • d3ebdafd4b update readme qiyuxinlin 2025-04-28 22:31:09 +00:00
  • 59b0631e33 update readme qiyuxinlin 2025-04-28 22:26:38 +00:00
  • 84d1f62daa deploy: ffb1f7bf09 qiyuxinlin 2025-04-28 22:18:55 +00:00
  • ffb1f7bf09 Merge pull request #1210 from kvcache-ai/support-amx-qwen wang jiahao 2025-04-29 06:18:45 +08:00
  • 8f76c37d86 fix readme qiyuxinlin 2025-04-28 22:17:22 +00:00
  • cb5617b479 update readme qiyuxinlin 2025-04-28 22:14:23 +00:00
  • 063c5489b3 fix can not compile amx qiyuxinlin 2025-04-28 21:52:14 +00:00
  • 27990dc6fb fix load bug qiyuxinlin 2025-04-28 21:08:13 +00:00
  • 74bb7fdcf6 Merge remote-tracking branch 'dev/support-amx-2' qiyuxinlin 2025-04-28 18:46:51 +00:00
  • be4b27e841 update doc qiyuxinlin 2025-04-28 18:24:15 +00:00
  • 33cbd47086 support qwen3 djw 2025-04-28 18:15:35 +00:00
  • 68c2b2e6e6 support qwen3 djw 2025-04-28 18:02:07 +00:00
  • 0da3792b27 support qwen3 djw 2025-04-28 14:05:24 +00:00
  • 3f9bbf1181 support qwen3, dont speak human language djw 2025-04-28 08:44:47 +00:00
  • 48c5ae23de deploy: ba92cf1a3b qiuqiu10 2025-04-28 07:10:39 +00:00
  • ba92cf1a3b Merge pull request #1204 from emmanuel-ferdman/main Chengyu Qiu 2025-04-28 15:10:14 +08:00
  • 27e3b2b98d Merge pull request #1202 from PC-DOS/main Chen Hongtao 2025-04-27 14:36:37 +08:00
  • cb80cb31a6 Update reference to optimize rules directory Emmanuel Ferdman 2025-04-26 01:43:18 -07:00
  • 5379e68f19 Replaced Chinese comments with English to avoid breaking MSVC compiling PC-DOS 2025-04-26 03:20:23 +08:00
  • 5b4d9c41ac Replaced Chinese comments with English to avoid breaking MSVC compiling PC-DOS 2025-04-26 03:18:01 +08:00
  • f3d842a0ca support AMX chenht2022 2025-04-25 14:47:16 +00:00
  • a7b995365e Merge pull request #1197 from jizhilong/jizhilong-patch-1 ZiWei Yuan 2025-04-25 14:50:58 +08:00
  • 82920e7943 :spakles: update requirements for cpufeature liam 2025-04-25 06:49:56 +00:00
  • b90362b5e6 Merge pull request #1198 from kvcache-ai/fix-max_new_tokens wang jiahao 2025-04-25 12:22:41 +08:00
  • 7af83f9efb fix load default max_new_tokens qiyuxinlin 2025-04-25 04:20:12 +00:00
  • 9a759e9fb8 fix: make cpufeature a local import jzl 2025-04-25 11:42:38 +08:00
  • 67042d11e3 Merge pull request #1193 from kvcache-ai/fix-chat-template-encoding Atream 2025-04-23 22:44:46 -06:00
  • 46493789eb fix chat template encoding Atream 2025-04-24 12:44:16 +08:00
  • 449a83dff6 Merge pull request #1183 from kvcache-ai/check-para wang jiahao 2025-04-23 16:27:18 +08:00
  • f7d939313b Merge remote-tracking branch 'origin/main' into check-para Alisehen 2025-04-23 02:40:14 +00:00
  • 99540ad01f add check parameters Alisehen 2025-04-23 02:38:43 +00:00
  • 7e4813e8ad Merge pull request #1184 from kvcache-ai/update_param wang jiahao 2025-04-22 20:55:11 +08:00
  • 3a044e6b14 change test qiyuxinlin 2025-04-22 12:50:39 +00:00
  • c995bdbbfa add check-para Alisehen 2025-04-22 09:30:08 +00:00
  • 739358789e Merge pull request #1182 from kvcache-ai/fix-kill-balance_serve wang jiahao 2025-04-22 17:28:06 +08:00
  • 4f9950e30c kill serve lead to kill sched and engine qiyuxinlin 2025-04-22 09:25:44 +00:00
  • 4c41f3a35f Merge pull request #1180 from kvcache-ai/update_param wang jiahao 2025-04-22 15:39:57 +08:00
  • b17ab8653c update speed test qiyuxinlin 2025-04-22 07:38:05 +00:00
  • 485588017b Merge pull request #1177 from kvcache-ai/update_param wang jiahao 2025-04-22 10:14:36 +08:00
  • f5287e908a fix no balance_serve import error qiyuxinlin 2025-04-22 02:11:18 +00:00
  • 03a65d6bea roll back ktransformers backend, add max_tokens, max_completion_tokens param qiyuxinlin 2025-04-21 12:55:37 +00:00
  • a1162eea01 Merge pull request #1158 from Creeper-MZ/function_call wang jiahao 2025-04-19 16:31:37 +08:00
  • 133ba746e9 优化提示词,解决部分Deepseek r1的兼容性 Creeper-MZ 2025-04-18 07:12:50 -04:00
  • 34c199403b Merge pull request #1170 from onepick/fix-cmake-error Atream 2025-04-18 07:51:03 -06:00
  • 0892d37d2d Merge pull request #1172 from kvcache-ai/move_create_sched wang jiahao 2025-04-18 18:19:29 +08:00
  • 38e841900d Move KV cache creation to balance_serve qiyuxinlin 2025-04-18 10:10:07 +00:00
  • c5edd3fdf0 Fix cmake config error onepick 2025-04-18 15:43:03 +08:00
  • e44c45e782 Merge pull request #1163 from cyhasuka/main Atream 2025-04-18 00:50:58 -06:00
  • 08f0bd5e13 Merge pull request #1168 from kvcache-ai/Atream-patch-1 Atream 2025-04-17 22:40:28 -06:00
  • e6fb4d5a58 remove hard code max_length Atream 2025-04-18 12:11:18 +08:00
  • 22a30d707d Merge pull request #1167 from kvcache-ai/update-llama4-tutorial-patch-1 Jianwei Dong 2025-04-18 11:44:11 +08:00
  • dfaf2b20fb update llama4 tutorial djw 2025-04-18 03:42:48 +00:00
  • 62c4023160 Fixed #1155 Creeper-MZ 2025-04-17 10:21:51 -04:00
  • eff5bbc202 Merge branch 'kvcache-ai:main' into main Yuhao Tsui 2025-04-17 22:01:31 +08:00
  • 4fb19bfcae Update chat.py Creeper-MZ 2025-04-17 09:19:14 -04:00
  • 8770b6d573 Merge pull request #1159 from onepick/fix-rocm-build-error ZiWei Yuan 2025-04-17 19:57:44 +08:00
  • 6a7624fe4a Change the logic to build device since cuda is as default onepick 2025-04-17 19:44:05 +08:00
  • 8ce34b3b5c Modify the performance calculation module Yuhao Tsui 2025-04-17 16:57:53 +08:00
  • 6e4da83d4b Merge pull request #978 from cyhasuka/main wang jiahao 2025-04-17 14:34:35 +08:00
  • b055132369 Merge pull request #1154 from 344303947/features/add-function-calling wang jiahao 2025-04-17 14:31:02 +08:00
  • 97f1995696 Fix some build error for ROCM onepick 2025-04-17 11:33:01 +08:00
  • cb266c98d4 Fix a bug Creeper-MZ 2025-04-16 23:31:33 -04:00
  • 3efb66213b Merge pull request #1157 from jiangshibiao/dev-fix-bug wang jiahao 2025-04-17 10:11:01 +08:00
  • 6bc2e85343 Update chat.py Creeper-MZ 2025-04-16 15:54:23 -04:00
  • 88f688e2c8 更改token注入逻辑,减少token注入量,防止遗忘 Creeper-MZ 2025-04-16 14:55:30 -04:00
  • 921061666c fix some bugs root 2025-04-17 00:48:09 +08:00
  • c8db24d5eb Update config.py kevin 2025-04-16 17:32:08 +08:00
  • badf7a1bb1 Merge branch 'kvcache-ai:main' into features/add-function-calling kevin 2025-04-16 17:21:27 +08:00
  • d2cf81423f Merge pull request #1135 from Creeper-MZ/function_call Chengyu Qiu 2025-04-16 09:57:22 +08:00
  • fcbd41e175 Merge pull request #1143 from jizhilong/improve-cmake-subprocess-output ZiWei Yuan 2025-04-15 17:37:44 +08:00
  • 0638ea298d feat(build): display limited tail of subprocesses in real time jizhilong 2025-04-15 16:40:38 +08:00
  • 8dc1ab9e04 Merge pull request #1108 from jizhilong/expose-cmake-logs ZiWei Yuan 2025-04-14 17:07:00 +08:00
  • 8699109129 Refactor the chat interface to support tool calling and parameter processing sean.su 2025-04-14 15:23:37 +08:00
  • a7e8d7c1af updata function_call Creeper-MZ 2025-04-13 23:48:51 -04:00
  • 038db30ec9 Merge pull request #1132 from wangkuigang-yewu-cmss/long-prompt-crash wang jiahao 2025-04-13 22:06:11 +08:00
  • 4538bdae97 prevent rpc process from crashing on long prompt wangkuigang-yewu-cmss 2025-04-13 16:12:18 +08:00
  • 797dac7e31 Merge pull request #1109 from aubreyli/libxxhash-fPIC ErvinXie 2025-04-13 14:15:31 +08:00
  • 77956822ce Merge pull request #1116 from ikawrakow/ik/add_copyright ZiWei Yuan 2025-04-13 11:53:12 +08:00
  • 99a247e167 Spelling Iwan Kawrakow 2025-04-11 10:15:42 +03:00
  • c46b0c59d0 Add missing references to ik_llama.cpp Iwan Kawrakow 2025-04-11 09:39:57 +03:00
  • 63ca2fa84d xxHash: fix link error due to non-position-independent code Aubrey Li 2025-04-10 21:50:23 +08:00
  • 690d4d42f9 chore: show cmake output in real time during build_ext jizhilong 2025-04-10 21:33:04 +08:00
  • 35ba63e259 Merge pull request #1103 from kvcache-ai/Atream-patch-6 Atream 2025-04-09 19:50:57 +08:00
  • 5f8cdc7640 Create SECURITY.md Atream 2025-04-09 19:50:38 +08:00
  • 92a67ab549 Merge pull request #1101 from kvcache-ai/Atream-patch-5 Atream 2025-04-09 19:23:46 +08:00
  • 98dbdcd66c Update llama4.md Atream 2025-04-09 19:23:35 +08:00
  • 9fad782c1a Merge pull request #1100 from kvcache-ai/Atream-patch-4 Atream 2025-04-09 19:10:03 +08:00
  • 346d202297 Update llama4.md Atream 2025-04-09 19:09:44 +08:00
  • a46c43b2db Merge pull request #1099 from kvcache-ai/Atream-patch-3 Atream 2025-04-09 18:01:46 +08:00
  • d1fcb208cc Update llama4.md Atream 2025-04-09 18:01:13 +08:00
  • 0774fe4d62 Merge pull request #1098 from kvcache-ai/Atream-patch-2 Atream 2025-04-09 17:58:44 +08:00
  • ed2b971e02 Update llama4.md Atream 2025-04-09 17:57:37 +08:00
  • c689b23364 Merge pull request #1097 from kvcache-ai/update-llama4-tutorial Jianwei Dong 2025-04-09 17:40:58 +08:00
  • 26798500bd update llama4 tutorial djw 2025-04-09 09:40:08 +00:00
  • 1e0be68e51 Merge pull request #1096 from kvcache-ai/update-llama4-tutorial Jianwei Dong 2025-04-09 17:37:33 +08:00
  • f73b4ca706 update llama4 tutorial djw 2025-04-09 09:36:30 +00:00