Commit Graph

2529 Commits

Author SHA1 Message Date
Tongbao Zhang
3980ff1be6 rename benchmark_deepgemm_fp8_group_gemm.py (#4605) 2025-03-23 23:35:20 -07:00
Stefan He
5d7edc8e55 Support FA3 as Attention backend by using --attention-backend fa3 (#4680)
Co-authored-by: qsong <qsong@linkedin.com>
Co-authored-by: qingquansong <ustcsqq@gmail.com>
2025-03-23 23:28:11 -07:00
Alex Sun
af6535e7aa [ROCm] Enable MTP (NextN) on AMD GPU (#4631) 2025-03-23 22:58:05 -07:00
c1lovez1
93cf7fc5cd Unify variable naming: replace is_in_free_group with is_not_in_free_group (#4698) 2025-03-23 21:51:08 -07:00
Kyungmin Lee
2a206b22ed Fix RotaryEmbedding when using Triton backend for EXAONE-3.5-2.4B (#4064) 2025-03-23 17:58:12 -07:00
Zhiqiang Xie
4d25305700 Move mem_state update into debug mode (#4525) 2025-03-23 00:52:27 -07:00
Mick
11577cedb7 refactor: bug fixes and refactor for vlm (#4661) 2025-03-22 22:48:49 -07:00
fzyzcjy
ca75741e86 Support async in DeepEP (#4610)
Co-authored-by: Cheng Wan <cwan39@gatech.edu>
2025-03-22 22:39:56 -07:00
fzyzcjy
c6d549e773 Multiple tiny code cleanups (#4608) 2025-03-22 22:39:11 -07:00
Yi Zhang
3c09548d1f close gemma2 in test_verl_engine.py temporarily (#4685) 2025-03-22 16:36:46 -07:00
BroadbentJim
8796cebb2c fix typo SGLang supports three grammar backends (#4679) 2025-03-22 14:33:48 -07:00
xutizhou
c2bd094d6e Optimize Permute Kernel in DeepEP (#4643)
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
2025-03-22 14:30:34 -07:00
Adarsh Shirawalmath
f8f9244a61 [Bug Fix] Add partial rotary factor support for Phi-4 and upgrade to transformers v4.50.0 (#3984)
Co-authored-by: Chayenne <zhaochen20@outlook.com>
2025-03-22 14:27:39 -07:00
Zhiqiang Xie
ecbfe58bb0 Bug fix for metrics counter (#4660) 2025-03-22 13:39:21 -07:00
Ke Bao
8f163b1653 Add EAGLE mtbench benchmark script (#4676)
Co-authored-by: chromecast56 <jamesll@mit.edu>
2025-03-22 13:34:01 -07:00
Yineng Zhang
e7a8610d51 fix flaky ut (#4670) 2025-03-22 12:36:50 -07:00
Adarsh Shirawalmath
a2cc62a6db [CI fix] test skipping modelopt on AMD (#4677) 2025-03-22 12:36:02 -07:00
Adarsh Shirawalmath
fb8886037c [Docs] Update docs for gemma3 and VLM chat templates (#4674) 2025-03-22 08:02:19 -07:00
AniZpZ
321ab756bc [1/3] fix dsv3 awq issue (#4556)
Co-authored-by: leoneo <1320612015@qq.com>
2025-03-22 01:07:17 -07:00
penguin_wwy
38f25e87fc Correcting default configuration when benchmarking fused_moe (#4665) 2025-03-22 00:52:34 -07:00
Yun Dai
8cd4250401 [quantization] fix channelwise conversion with scalar weight scale (#4596) 2025-03-22 00:47:52 -07:00
Chunan Zeng
6a384d5c01 Speed up per token and per tensor quant by 15% (#4639) 2025-03-22 00:37:57 -07:00
Yineng Zhang
f69e0696bc update news for README (#4664) 2025-03-21 23:25:59 -07:00
mlmz
f6ab4ca6bc fix: fix ipython running error for Engine due to outlines nest_asyncio (#4582)
Co-authored-by: shuaills <shishuaiuoe@gmail.com>
2025-03-21 19:11:15 -07:00
Byron Hsu
c7c7dbebbe [PD] Release initial code (#4654)
Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: Ying1123 <sqy1415@gmail.com>
Co-authored-by: merrymercy <lianminzheng@gmail.com>
Co-authored-by: makro
Co-authored-by: dhou-xai
2025-03-21 14:47:47 -07:00
Yuhong Guo
417fc72f6f Align completion and chat_completion response to OpenAI API (#4637) 2025-03-20 22:59:04 -07:00
Michael Yao
c6ec70290f [docs] Add links and fix grammars in deploy_on_k8s.md (#4641)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
2025-03-20 22:55:23 -07:00
lukec
4c56e5dbee Set deepgemm to the default value in the hopper architecture. (#4613) 2025-03-20 22:03:00 -07:00
Cheng Wan
7b5fc71972 fix SUPPORT_CUTLASS_BLOCK_FP8 flag (#4640) 2025-03-20 21:45:07 -07:00
Shu Wang
ad4e58bf67 Support fp8 gemm for blackwell (#4558) 2025-03-20 12:40:28 -07:00
Ke Bao
bfb03c6182 Update doc for MTP and DP attention (#4622) 2025-03-20 11:31:48 -07:00
Yuhong Guo
b36ab493b3 Enable setting sglang logger from Env Variable SGLANG_LOGGING_CONFIG_PATH (#4592)
Signed-off-by: Yuhong Guo <yuhong.gyh@antgroup.com>
2025-03-20 02:10:32 -07:00
JieXin Liang
9e93ef3f8e [fix] fix illegal mem access and clean up triton attention backend (#4571) 2025-03-20 02:01:52 -07:00
Chuyue Sun
fad86a6863 Support n in OpenAI API completions (#3446)
Co-authored-by: Shan Yu <shanyu1@g.ucla.edu>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
Co-authored-by: chuyue sun <chuyue@lmsys.us-northcentral1-a.compute.internal>
2025-03-20 13:46:46 +08:00
strgrb
df7014a8d2 avoid cudaStreamSynchronize in DeepSeekV2AttentionMLA (#4577)
Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
2025-03-19 10:02:26 -07:00
JieXin Liang
4942074174 [fix] fix initialization of _ENABLE_TORCH_INFERENCE_MODE (#4549) 2025-03-19 09:57:59 -07:00
Hongbo Xu
ba52fd1868 Add clang-format to pre-commit config (#4583) 2025-03-19 09:50:19 -07:00
lukec
b6944f97a6 Support FlashMLA backend cuda graph (#4514)
Co-authored-by: yinfan98 <1106310035@qq.com>
Co-authored-by: Hongbosherlock <hongbosherlock@gmail.com>
Co-authored-by: ispobock <ispobaoke@163.com>
2025-03-19 08:25:34 -07:00
Jinyan Chen
f44db16c8e [Feature] Integrate DeepEP into SGLang (#4232)
Co-authored-by: Cheng Wan <cwan39@gatech.edu>
Co-authored-by: Xuting Zhou <xutingz@nvidia.com>
2025-03-19 08:16:31 -07:00
strgrb
f9c53cbb42 Create col-major and tma-aligned x_scale for deep_gemm.gemm_fp8_fp8_bf16_nt (#4515)
Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
2025-03-19 00:02:43 -07:00
Baizhou Zhang
90532b7627 [Fix] Fix raw_bs bug when using flashinfer mla and eagle (#4557) 2025-03-18 21:26:53 -07:00
JieXin Liang
c0e9a36c5f Optimize Triton decoding kernel for dynamic workload (#4553) 2025-03-18 21:25:38 -07:00
aoshen524
588865f0e0 [Feature] Support Tensor Parallelism and Weight Slicing for Lora (#4274)
Co-authored-by: ShenAo1111 <1377693092@qq.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
2025-03-18 20:33:07 -07:00
Cheng Wan
3196999f63 Reduce computation and communication in DP attention (#4521) 2025-03-18 13:41:36 -07:00
James Liu
9e0186f352 [Feature] Support EAGLE 3 (#4247) 2025-03-18 07:35:23 -07:00
Wei Wu
8baf9a0c18 [Fix] Type annotation correction for UpdateWeightsFromTensorReqInput (#4532)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2025-03-18 00:52:47 -07:00
Yineng Zhang
c787298547 use sgl custom all reduce (#4441) 2025-03-18 00:46:41 -07:00
Ke Bao
45212ce18b Add deepseek v2 torch compile pr test (#4538) 2025-03-18 00:29:24 -07:00
Yineng Zhang
c16b33ccac cleanup deps 3/n (#4541) 2025-03-18 00:11:36 -07:00
Albert
2d0045125f Fix the incorrect args in benchmark_and_profiling.md (#4542)
Signed-off-by: Tianyu Zhou <albert.zty@antgroup.com>
2025-03-18 00:07:06 -07:00