Commit Graph

  • cc367f5814 Merge pull request #1351 from kvcache-ai/load-DeepSeek-0528 Atream 2025-06-01 19:13:57 +08:00
  • a6b3243a56 [Patch] lload DeepSeek-R1-0528 qiyuxinlin 2025-05-31 14:19:20 +00:00
  • ac48a58cca Merge pull request #1350 from kvcache-ai/Update-WeChatGroup Atream 2025-05-31 13:34:14 +08:00
  • 44143d972f Add files via upload Atream 2025-05-31 13:33:36 +08:00
  • d8bc6402b5 raise exception on device error (#1342) Emmanuel Ferdman 2025-05-29 10:37:41 +03:00
  • 00949d5e8d Mirror #1247 in server mode Ye Zhou 2025-05-29 15:30:26 +08:00
  • 54197ec794 deploy: ce75fcd7dd aubreyli 2025-05-28 06:09:07 +00:00
  • ce75fcd7dd Merge pull request #1337 from liu-shaojun/docker_xpu aubreyli 2025-05-28 14:08:46 +08:00
  • 404ad39a04 docs: add Dockerfile.xpu and GPU driver setup instructions Shaojun Liu 2025-05-26 14:35:14 +08:00
  • 0c44f2e211 Merge pull request #1331 from rnwang04/qwen3_xpu_support wang jiahao 2025-05-23 10:38:28 +08:00
  • 71a5fc5770 fix local_chat.py chunk_size not effect experts qiyuxinlin 2025-05-23 02:35:01 +00:00
  • adc0906967 add XPU support for qwen3moe local chat rnwang04 2025-05-21 18:33:41 +08:00
  • 25893366b6 Merge pull request #1328 from chenht2022/main Chen Hongtao 2025-05-21 11:46:48 +08:00
  • 66453981ff Fix NaN bug chenht2022 2025-05-21 03:39:49 +00:00
  • 7d79735bd0 Merge pull request #1323 from kvcache-ai/Atream-patch-2 Atream 2025-05-19 23:21:56 +08:00
  • 4f78e37625 Update version Atream 2025-05-19 23:21:23 +08:00
  • 01311d251d Merge pull request #1320 from aubreyli/no_cuda_graph_err Atream 2025-05-18 02:45:05 -06:00
  • d347aeb518 VLinearMarlin: padding to input.shape[0] to avoid CUDA error Aubrey Li 2025-05-18 15:11:37 +08:00
  • c350679d2e deploy: 32f3d7befb qiyuxinlin 2025-05-17 07:25:56 +00:00
  • 32f3d7befb Merge pull request #1307 from kvcache-ai/hyc v0.3.1 wang jiahao 2025-05-17 15:25:33 +08:00
  • 5b08d5b07b fix Alisehen 2025-05-17 07:22:51 +00:00
  • 551ebc91c7 Merge pull request #1313 from rnwang04/update_ipex_llm_version aubreyli 2025-05-16 13:28:12 +08:00
  • a56aa45186 fix ipex-llm version to 2.3.0rc1 rnwang04 2025-05-16 12:19:37 +08:00
  • a3346c9a41 Merge pull request #1311 from kvcache-ai/wx-csy-patch-1 aubreyli 2025-05-16 08:28:23 +08:00
  • 5d194c5db0 Fix typos Shaoyuan CHEN 2025-05-15 22:15:55 +08:00
  • f3b1e36b6a bug fix Alisehen 2025-05-15 10:01:51 +00:00
  • d5a50ab494 deploy: 7faa776659 Atream 2025-05-15 07:58:13 +00:00
  • 7faa776659 Merge pull request #1277 from Coekjan/patch-1 Atream 2025-05-15 01:58:00 -06:00
  • edd9efa49e fix Alisehen 2025-05-15 07:28:50 +00:00
  • 055680e26c add flashinfer to cuda device Alisehen 2025-05-15 07:03:45 +00:00
  • f3be33a313 add xpu parameters to install.sh Alisehen 2025-05-15 06:39:02 +00:00
  • af9472b518 Merge pull request #1306 from aubreyli/xpu-doc aubreyli 2025-05-15 14:18:47 +08:00
  • 72f6d93ffd xpu.md: add device discovery tips Aubrey Li 2025-05-15 14:12:26 +08:00
  • 8caecf37d8 Merge pull request #1305 from kvcache-ai/update-readme wang jiahao 2025-05-15 12:10:20 +08:00
  • b40f13abeb fix deduplicate_and_sort cudagraphs qiyuxinlin 2025-05-15 04:09:34 +00:00
  • a475aaae4a deploy: 09f0ddc00b aubreyli 2025-05-15 02:56:10 +00:00
  • 09f0ddc00b Merge pull request #1303 from rnwang04/fix_typo_and_style aubreyli 2025-05-15 10:55:58 +08:00
  • 2f6e14a54b fix md typo, fix code style, and update setup value error message rnwang04 2025-05-15 09:14:59 +00:00
  • 07c5f23da5 Merge pull request #1304 from kvcache-ai/Atream-patch-1 Atream 2025-05-14 20:29:54 -06:00
  • d051a14941 Update README.md Atream 2025-05-15 10:29:43 +08:00
  • 4044e8c7fa deploy: 2d3aaef8b6 qiyuxinlin 2025-05-14 13:16:04 +00:00
  • 2d3aaef8b6 Merge pull request #1301 from kvcache-ai/update-readme wang jiahao 2025-05-14 21:15:55 +08:00
  • d35d61f6a1 update readme qiyuxinlin 2025-05-14 13:15:18 +00:00
  • c3d0ac80c6 update readme qiyuxinlin 2025-05-14 13:13:10 +00:00
  • ee524b0f41 Merge pull request #1300 from kvcache-ai/qiyuxinlin-patch-1 wang jiahao 2025-05-14 21:09:20 +08:00
  • 9fe3f35c37 Update install.sh wang jiahao 2025-05-14 21:08:58 +08:00
  • 34225e8c93 deploy: f7ee993fdc aubreyli 2025-05-14 12:58:47 +00:00
  • f7ee993fdc Merge pull request #1295 from rnwang04/xpu_support aubreyli 2025-05-14 20:58:35 +08:00
  • 142fb7ce6c Enable support for Intel XPU devices, add support for DeepSeek V2/V3 first rnwang04 2025-05-14 14:28:22 +00:00
  • 333351c7c8 Merge pull request #1298 from kvcache-ai/fix-workspace-buffer wang jiahao 2025-05-14 17:50:40 +08:00
  • ecc01cda17 update norm cpu kernel qiyuxinlin 2025-05-14 09:49:35 +00:00
  • 8974cc9d75 Merge pull request #1297 from kvcache-ai/fix-workspace-buffer wang jiahao 2025-05-14 17:46:55 +08:00
  • 64742bec83 update torch MLA kernel qiyuxinlin 2025-05-14 09:45:12 +00:00
  • 4e015ccc65 Merge pull request #1296 from kvcache-ai/fix-workspace-buffer wang jiahao 2025-05-14 17:35:27 +08:00
  • e8e83308a9 fix flashinfer float_workspace_buffer small qiyuxinlin 2025-05-14 09:33:52 +00:00
  • 02948bc1b8 Merge pull request #1289 from kvcache-ai/update-default-config wang jiahao 2025-05-13 20:23:25 +08:00
  • 697444905a update default config qiyuxinlin 2025-05-13 12:20:21 +00:00
  • 8456222852 Merge pull request #1276 from kvcache-ai/support_load_safetensor wang jiahao 2025-05-12 11:10:26 +08:00
  • 1edc6d9de0 Fix typo about GLIBCXX_3.4.32 Yip Coekjan 2025-05-09 20:34:45 +08:00
  • c6aa379de2 support safetensor load, delete architectures argument qiyuxinlin 2025-05-09 10:38:29 +00:00
  • 30eab48a75 Merge pull request #799 from aubreyli/cpu_offloading Atream 2025-05-09 00:38:54 -06:00
  • 8025def197 Merge pull request #1246 from aubreyli/GenerationMixin Atream 2025-05-09 00:35:15 -06:00
  • 900a7f7c3e Merge pull request #1271 from kvcache-ai/fix-AMX Atream 2025-05-07 05:12:38 -06:00
  • b22cded890 fix AMX Atream 2025-05-07 19:12:19 +08:00
  • 671151f6e7 deploy: 3f14e311cb Alisehen 2025-05-07 07:22:46 +00:00
  • 3f14e311cb Merge pull request #1247 from aubreyli/_get_logits_warper Yaochen Han 2025-05-07 15:22:35 +08:00
  • b3a1fcf471 ktransformers/utils: fix _get_logits_warper error Aubrey Li 2025-05-01 08:05:35 +08:00
  • def1ec7683 modeling_deepseek_v3: fix GenerationMixin warning Aubrey Li 2025-05-01 07:48:15 +08:00
  • 7530491f5b Merge pull request #1244 from kvcache-ai/update-custom-flashinfer Atream 2025-04-30 04:46:19 -06:00
  • 753075728c update-custom-flashinfer Atream 2025-04-30 10:45:25 +00:00
  • a4bd6818ed Merge pull request #1241 from kvcache-ai/fix-cache-lens Atream 2025-04-29 21:38:12 -06:00
  • 7adb7281f4 fix-cache-lens Atream 2025-04-30 03:37:43 +00:00
  • 8ba7e5d4b8 Merge pull request #1227 from kvcache-ai/change-yaml wang jiahao 2025-04-29 16:10:37 +08:00
  • 48dfbc8f9f change inject yaml qiyuxinlin 2025-04-29 08:09:39 +00:00
  • 2a224b256e Merge pull request #1225 from kvcache-ai/fix_typo_main ZiWei Yuan 2025-04-29 13:26:02 +08:00
  • 0e8a36770a ✨ update ignore liam Yuan 2025-04-29 13:24:14 +08:00
  • c519747f3c Merge pull request #1224 from kvcache-ai/fix_typo_main ZiWei Yuan 2025-04-29 13:22:27 +08:00
  • 2762012039 ✨ fix typo liam Yuan 2025-04-29 13:20:03 +08:00
  • ab26e7d7db Merge pull request #1223 from kvcache-ai/fix-client Atream 2025-04-28 22:35:04 -06:00
  • 0f7a3e5fea fix-client Atream 2025-04-29 12:34:20 +08:00
  • cc94a02ab5 Merge pull request #1222 from kvcache-ai/fix-compile Atream 2025-04-28 22:13:09 -06:00
  • 08035a7cda Update requirements-local_chat.txt Atream 2025-04-29 12:12:35 +08:00
  • fd9876049d Update pyproject.toml Atream 2025-04-29 12:11:11 +08:00
  • 9d6e09efa6 Merge pull request #1221 from kvcache-ai/Atream-patch-5 Atream 2025-04-28 21:14:10 -06:00
  • 28948aacc9 Update AMX.md Atream 2025-04-29 11:12:51 +08:00
  • bee6291dc2 Merge pull request #1220 from kvcache-ai/fix-hopper-flashinfer Atream 2025-04-28 21:07:34 -06:00
  • b0318fc01c fix-hopper-flashinfer Atream 2025-04-29 11:06:34 +08:00
  • b703cc9c3d Merge pull request #1219 from kvcache-ai/Atream-patch-4 Atream 2025-04-28 21:04:12 -06:00
  • 14efb15593 Update AMX.md Atream 2025-04-29 11:03:59 +08:00
  • 38333cf129 Merge pull request #1218 from kvcache-ai/clean-up Atream 2025-04-28 20:36:25 -06:00
  • 192746cf93 clean-up Atream 2025-04-29 10:32:42 +08:00
  • e4538bc013 Merge pull request #1217 from kvcache-ai/Atream-patch-3 Atream 2025-04-28 20:31:03 -06:00
  • 073ce601e0 Update AMX.md Atream 2025-04-29 10:29:51 +08:00
  • 2bcdf10fbb Merge pull request #1216 from kvcache-ai/Atream-patch-2 Atream 2025-04-28 19:58:56 -06:00
  • e8b2bf4f7b Update version info in __init__.py Atream 2025-04-29 09:58:40 +08:00
  • 5599fef98f Merge pull request #1215 from kvcache-ai/Atream-patch-1 Atream 2025-04-28 19:43:29 -06:00
  • 7ebf82a492 Update Qwen3 date Atream 2025-04-29 09:43:13 +08:00
  • f27e4850f1 Merge pull request #1212 from kvcache-ai/support-amx-qwen wang jiahao 2025-04-29 07:09:53 +08:00
  • e70db18b63 update AMX readme qiyuxinlin 2025-04-28 23:08:38 +00:00
  • 2e905c8bd4 update AMX readme qiyuxinlin 2025-04-28 23:03:32 +00:00