EngineX/xc-llm-kunlun
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Commit Graph

  • 1c21b07232 Merge pull request #56 from tanjunchen/main-dev-02 Xinyu Dong 2025-12-28 17:47:49 +08:00
  • 99269e3ce9 add PULL_REQUEST_TEMPLATE.md and ISSUE_TEMPLATE tanjunchen 2025-12-27 22:03:56 +08:00
  • 0efa514bd9 1.add CODE_OF_CONDUCT.md to vLLM Kunlun 2.add MAINTAINERS.md to vLLM Kunlun 3.add MAINTAINERS.md to vLLM Kunlun 4.add contributing guide to vLLM Kunlun tanjunchen 2025-12-23 21:57:30 +08:00
  • 45c6b8e927 Merge pull request #52 from liwei109/awq_gptq baoqian426 2025-12-24 17:05:26 +08:00
  • ed90690bd3 Merge pull request #50 from liwei109/quant baoqian426 2025-12-24 17:05:04 +08:00
  • 6546323c71 [dev] support AWQ/GPTQ quantization for dense models Li Wei 2025-12-24 13:45:55 +08:00
  • 383eb5459a [refactor] remove redundant code in linear Li Wei 2025-12-24 12:02:09 +08:00
  • 75d0bdae2f Merge pull request #40 from ldh2020/v0.11.0dev Xinyu Dong 2025-12-22 21:50:27 +08:00
  • c91134fd09 Merge pull request #39 from LiangYC1021/v0.11.0dev Xinyu Dong 2025-12-22 19:33:17 +08:00
  • a4b9e92ca1 [Kernel] Replace native torch solve_tril by solve_tril_fwd kernel op hanhaowen 2025-12-22 17:37:19 +08:00
  • 059988adbc Merge pull request #2 from ldh2020/ldh2020-qwen3-next ldh2020 2025-12-22 11:11:01 +08:00
  • 8261a09e2a [Kernel] Optimize the selection and update OP of ssm state ldh2020 2025-12-21 15:45:32 +08:00
  • b97c781300 [Kernel] Optimize the recurrent op ldh2020 2025-12-21 11:22:06 +08:00
  • 004e164bdb [Kernel] Optimize the recurrent op ldh2020 2025-12-21 11:18:00 +08:00
  • 58c1db5073 [Bugfix] fix the bug of the flash_attention in Qwen3-Next ldh2020 2025-12-21 10:34:43 +08:00
  • 911b886e9d [Docs] Update installation.md Xinyu Dong 2025-12-20 10:16:57 +08:00
  • 6f96615ee3 Merge pull request #23 from ldh2020/v0.11.0dev Xinyu Dong 2025-12-19 15:26:18 +08:00
  • 92ce826ece Merge pull request #30 from baidu/28-v0110-only-enble-top-p-or-k-occur-error chenyili0619 2025-12-18 13:05:45 +08:00
  • ff7131678a Merge pull request #29 from chenyili0619/28-v0110-only-enble-top-p-or-k-occur-error Xinyu Dong 2025-12-18 13:04:39 +08:00
  • 2e2933d217 [Bug] Fixed the issue where an error occurred when the request included a seed. chenyili0619 2025-12-18 13:03:34 +08:00
  • fce97df908 [Kernel] Use l2norm kernel op instead of triton op. ldh2020 2025-12-16 16:24:47 +08:00
  • 6b5740ad0a [Docs] Fix Docs Xinyu Dong 2025-12-16 16:04:29 +08:00
  • f6a73ac442 [Docs] Update installation.md, Fix Ops Merge pull request #21 from baidu/18-qwen3-30b-a3b-instruct-2507-tool-calling-issue Xinyu Dong 2025-12-16 14:59:57 +08:00
  • 8fb42b1c9a [Docs] Update installation.md Xinyu Dong 2025-12-16 14:49:12 +08:00
  • aa770e6946 [Model] Support llama3 on v0.11.0 Merge pull request #19 from xyDong0223/v0.11.0dev Xinyu Dong 2025-12-16 14:15:58 +08:00
  • 5a75795ade [Model] Update llama.py Xinyu Dong 2025-12-15 21:28:56 +08:00
  • 7c7d0326c5 [Model] registry llama.py to vLLM Xinyu Dong 2025-12-15 21:21:28 +08:00
  • ca059110b3 [Model] Supporet llama3 on v0.11.0 Xinyu Dong 2025-12-15 21:20:44 +08:00
  • ab23c082b8 [Kernel] Optimize the performance of causal_conv1d. Merge pull request #15 from ldh2020/v0.11.0dev Xinyu Dong 2025-12-12 18:04:33 +08:00
  • a6310d36ea Merge branch 'baidu:v0.11.0dev' into v0.11.0dev ldh2020 2025-12-12 17:43:52 +08:00
  • bec4ad4f91 Merge pull request #1 from ldh2020/ldh2020-causal_conv1d ldh2020 2025-12-12 17:43:18 +08:00
  • bb3b5a52cb Merge pull request #13 from ldh2020/v0.11.0dev Xinyu Dong 2025-12-12 17:37:46 +08:00
  • cff4727fbb [Kernel] Optimize the performance of causal_conv1d. ldh2020 2025-12-12 17:22:35 +08:00
  • 9bb2ee06a4 [Bugfix] fix the bug of torch_solve_tril ldh2020 2025-12-12 17:01:50 +08:00
  • fae22c2e62 Merge pull request #3 from xyDong0223/main baoqian426 2025-12-11 11:47:30 +08:00
  • af2cd6097f [Kernell] fix miss import os xyDong0223 2025-12-11 11:17:28 +08:00
  • 0b7fb2ad19 Delete docs/source/developer_guide/evaluation/accuracy_report/Qwen3-30B-A3B-coder.md xyDong0223 2025-12-10 21:58:27 +08:00
  • f4bf3a6251 Delete docs/source/developer_guide/evaluation/accuracy_report/Qwen2.5-32B.md xyDong0223 2025-12-10 21:58:16 +08:00
  • 170e7091d1 Delete docs/source/developer_guide/evaluation/accuracy_report/Qwen3-8B.md xyDong0223 2025-12-10 21:58:03 +08:00
  • 670c2397b8 [Kernel] Enable fast random sample on Kunlun P xyDong0223 2025-12-10 21:52:48 +08:00
  • 0d4d4967cf Update README.md xyDong0223 2025-12-10 21:46:18 +08:00
  • 02c2da9c7a remove rebudant files chenyili 2025-12-10 20:31:44 +08:00
  • f109a76a39 Merge pull request #2 from WeiJie-520/main xyDong0223 2025-12-10 20:24:05 +08:00
  • bd66cfa6c2 [Doc] Update Qwen model accuracy report hongweijie 2025-12-10 17:55:27 +08:00
  • 7c22d621fb 提交vllm0.11.0开发分支 chenyili 2025-12-10 17:51:24 +08:00
  • deab7dd0b6 Update README.md xyDong0223 2025-12-10 17:28:00 +08:00
  • d6c0c6b126 Merge pull request #1 from caijizhuo/main xyDong0223 2025-12-10 17:09:50 +08:00
  • b614823125 [chore] Remove obsolete comments zhaoyingzhuo 2025-12-10 15:52:23 +08:00
  • ec935627cb [Doc] Update README dongxinyu03 2025-12-10 14:59:29 +08:00
  • 1b343812c9 [Doc] Update docs dongxinyu03 2025-12-10 14:46:12 +08:00
  • a3d11f9b73 [Doc] Update docs dongxinyu03 2025-12-10 14:26:37 +08:00
  • 3762e6e3ab [Doc] Update docs dongxinyu03 2025-12-10 14:16:10 +08:00
  • c728e52505 Initial commit for vLLM-Kunlun Plugin dongxinyu03 2025-12-10 12:05:39 +08:00