EngineX/xc-llm-kunlun
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
92 Commits 2 Branches 0 Tags
ff8ebfa2087dd9d04d216389921d7a20f2c3f142
Commit Graph

41 Commits

Author SHA1 Message Date
hanhaowen
ff8ebfa208 enable full cudagraph for deepseek 2026-01-12 15:18:12 +08:00
roger-lcc
0455b49519 [Bugs] fix qwen2_vl for 0.11.0 (#94) 
Co-authored-by: luochencheng <luochencheng@baidu.com>
 2026-01-09 15:05:40 +08:00
baoqian426
2c9b176e6e [Feature] use for dp (#90) 2026-01-08 11:05:48 +08:00
baoqian426
eb40e8a07a [Bugfix] fix can not import compressed_tensors (#87) 
Co-authored-by: root <root@rdtest-node1150.bcc-zwlt.baidu.com>
 2026-01-07 11:32:10 +08:00
Li Wei
1c1b84d78c [fix]update compressed-tensors scheme 
Deepseek v3.2 is supported now

Signed-off-by: Li Wei <liwei.109@outlook.com>
 2026-01-06 22:30:27 +08:00
baoqian426
9c2b908908 Merge pull request #84 from xyDong0223/main 
[Feature] DeepSeek Support MTP
 2026-01-06 21:56:31 +08:00
dongxinyu03
26b311ccf5 [Feature] DeepSeek Support MTP 2026-01-06 21:37:21 +08:00
tangshiwen
f811ae968a [fix] resolve cutlass_scaled_mm inference error 2026-01-06 20:52:12 +08:00
Li Wei
9533f68e99 [fix]matmul not support cuda graph 2026-01-06 17:32:45 +08:00
Li Wei
515a4eeda9 [dev] support compressed-tensors w8a8 quantization (#75) 
* [dev] support compressed-tensors w8a8 quantization

Co-authored-by: Li Wei <liwei.109@outlook.com>

* [refact]update KunlunScaleMMKernel impl

* [rebase]resolve conflicts and remove redundant code

---------

Co-authored-by: tangshiwen <tangshiwen@baidu.com>
 2026-01-06 13:51:53 +08:00
baoqian426
ee0f50e68f [Feature] support deepseek v3/r1/v3.2 (#78) 
* [Feature] support deepseek v3/r1/v3.2

* fix gpt_oss

* update readme

* update readme

---------

Co-authored-by: hanhaowen <hanhaowen@baidu.com>
 2026-01-05 22:55:35 +08:00
Xinyu Dong
07bc24a555 [Bugs] Fix moe when without bias (#76) 2026-01-05 10:51:23 +08:00
callmelaoyi
b86953acf9 [Kernel] Qwen3-next 优化 recompute_w_u_fwd & chunk_fwd_o (#74) 
Co-authored-by: yuanjizhong <yuanjizhong@baidu.com>
 2026-01-05 10:24:51 +08:00
Xinyu Dong
fe666fb24f [Feature] Support gpt-oss and update model list (#71) 
* [Docs] Update Support Models

* [Feature] Support gpt-oss

* [Docs] fix model support list

* Fix Moe

* Fix

* Fix moe_ep

* remove gpt oss graph support , not yet

---------

Co-authored-by: hanhaowen <hanhaowen@baidu.com>
 2026-01-04 21:19:49 +08:00
Joeegin
ded24f5026 [Model] Supporet InternVL2_5 on v0.11.0 (#72) 
Co-authored-by: v_qiaoyijin <v_qiaoyijin@baidu.com>
 2026-01-04 16:38:05 +08:00
hanhaowen
b015bb76fd remove qwen2.py llama.py fix llama output 2025-12-31 11:39:37 +08:00
Xinyu Dong
b3c30a3cb9 [Feature] Support XiaoMi MIMO Flash V2 (#62) 
* [Feature] Support MIMO Flash V2
 2025-12-31 10:16:33 +08:00
Li Wei
9cee025f41 Merge pull request #59 from liwei109/aicapx-quant 
[fix]remove weight_loader_v2 to suport cuda graph
 2025-12-29 19:56:24 +08:00
baoqian426
45c6b8e927 Merge pull request #52 from liwei109/awq_gptq 
[dev] support AWQ/GPTQ quantization for dense models
 2025-12-24 17:05:26 +08:00
Li Wei
6546323c71 [dev] support AWQ/GPTQ quantization for dense models 2025-12-24 13:46:06 +08:00
Li Wei
383eb5459a [refactor] remove redundant code in linear 2025-12-24 12:02:09 +08:00
Xinyu Dong
75d0bdae2f Merge pull request #40 from ldh2020/v0.11.0dev 
[Kernel] Optimize the performance of Qwen3-Next
 2025-12-22 21:50:27 +08:00
hanhaowen
a4b9e92ca1 [Kernel] Replace native torch solve_tril by solve_tril_fwd kernel op 2025-12-22 17:37:19 +08:00
ldh2020
8261a09e2a [Kernel] Optimize the selection and update OP of ssm state 2025-12-21 15:45:32 +08:00
ldh2020
b97c781300 [Kernel] Optimize the recurrent op 2025-12-21 11:22:06 +08:00
ldh2020
004e164bdb [Kernel] Optimize the recurrent op 2025-12-21 11:18:00 +08:00
ldh2020
58c1db5073 [Bugfix] fix the bug of the flash_attention in Qwen3-Next 2025-12-21 10:34:43 +08:00
Xinyu Dong
6f96615ee3 Merge pull request #23 from ldh2020/v0.11.0dev 
[Kernel] Use l2norm kernel op instead of triton op.
 2025-12-19 15:26:18 +08:00
chenyili0619
2e2933d217 [Bug] Fixed the issue where an error occurred when the request included a seed. 2025-12-18 13:03:34 +08:00
ldh2020
fce97df908 [Kernel] Use l2norm kernel op instead of triton op. 2025-12-16 16:24:47 +08:00
Xinyu Dong
5a75795ade [Model] Update llama.py 
Remove redundancy
 2025-12-15 21:28:56 +08:00
Xinyu Dong
7c7d0326c5 [Model] registry llama.py to vLLM 2025-12-15 21:21:28 +08:00
Xinyu Dong
ca059110b3 [Model] Supporet llama3 on v0.11.0 
FULL AND PIECEWISE GRAPH ENBALE
 2025-12-15 21:20:44 +08:00
ldh2020
cff4727fbb [Kernel] Optimize the performance of causal_conv1d. 2025-12-12 17:22:35 +08:00
ldh2020
9bb2ee06a4 [Bugfix] fix the bug of torch_solve_tril 2025-12-12 17:01:50 +08:00
baoqian426
fae22c2e62 Merge pull request #3 from xyDong0223/main 
[Kernel] Enable fast random sample on Kunlun3 Platform
 2025-12-11 11:47:30 +08:00
xyDong0223
af2cd6097f [Kernell] fix miss import os 2025-12-11 11:17:28 +08:00
xyDong0223
670c2397b8 [Kernel] Enable fast random sample on Kunlun P 2025-12-10 21:52:48 +08:00
chenyili
7c22d621fb 提交vllm0.11.0开发分支 2025-12-10 17:51:24 +08:00
zhaoyingzhuo
b614823125 [chore] Remove obsolete comments 2025-12-10 15:52:23 +08:00
dongxinyu03
c728e52505 Initial commit for vLLM-Kunlun Plugin 2025-12-10 12:05:39 +08:00