Commit Graph

2994 Commits

Author SHA1 Message Date
IAN
11e27d0926 [PD]: Support Muti Prefill in one node (#5704)
Co-authored-by: shuaills <shishuaiuoe@gmail.com>
2025-04-26 00:30:47 +08:00
shangmingc
50eda8398e [PD] Add kvargs table and thread pool for kvcache sender of mooncake (#5738)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-04-25 18:15:01 +08:00
Liangsheng Yin
c55550cbf0 [PD] Better logs (#5715) 2025-04-25 17:25:45 +08:00
Brayden Zhong
43fb95c2fa [Model] Support ArcticForCausalLM architecture (Snowflake/snowflake-arctic-instruct) (#5078)
Co-authored-by: vincent-4 <vincentzhongy+githubvincent4@gmail.com>
2025-04-25 15:24:09 +08:00
Ravi Theja
7d9679b74d Add MMMU benchmark results (#4491)
Co-authored-by: Ravi Theja Desetty <ravitheja@Ravis-MacBook-Pro.local>
2025-04-25 15:23:53 +08:00
Michael Yao
b5be56944b [Doc] Fix a link to Weilin Zhao (#5706)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
2025-04-25 02:02:27 +08:00
Ravi Theja
d2b8d0b8d8 Add example to use sgl engine with fastapi (#5648)
Co-authored-by: Ravi Theja Desetty <ravitheja@Ravis-MacBook-Pro.local>
2025-04-24 23:57:05 +08:00
Baizhou Zhang
a14654dd68 Fix weight loading bug for Deepseek v3+nextn (#5684) 2025-04-24 21:29:56 +08:00
Yuhong Guo
5d93a950ee [BugFix] Fix combination of MTP and --n-share-experts-fusionwith R1 (#5707) 2025-04-24 21:13:51 +08:00
Mick
c998d04b46 vlm: enable radix cache for qwen-vl models (#5349)
Co-authored-by: Xinyuan Tong <justinning0323@outlook.com>
2025-04-23 20:35:05 -07:00
Yineng Zhang
7d0edf3cae chore: bump sgl-kernel 0.1.0 (#5688) 2025-04-23 14:23:59 -07:00
Yineng Zhang
ce4ecba477 fix: only compile ApplyTokenBitmaskInplace cu124+ (#5686) 2025-04-23 14:17:42 -07:00
Yineng Zhang
b1f6d89b5f fix: update truss bench_serving (#5683) 2025-04-23 13:28:35 -07:00
Michael Yao
7c99103f4c [Doc] Fix two 404 links caused by sglang typo (#5667)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
2025-04-23 23:21:55 +08:00
Lianmin Zheng
de071366cd tune the threshold of gemma-2-27b-it in test_nightly_gsm8k_eval.py (#5677) 2025-04-23 05:31:17 -07:00
shangmingc
e0673969b9 [PD] Add support for dp attention with mooncake (#5530)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-04-23 17:20:27 +08:00
Yineng Zhang
127ff8982e fix torchvision::nms not exist (#5671) 2025-04-23 02:17:21 -07:00
Yineng Zhang
8777a1d24b fix gemma3 unit test (#5670) 2025-04-23 02:14:01 -07:00
Cheng Wan
711efe7814 Integrating PD disaggregation with DP attention and DeepEP (#5435)
Co-authored-by: Byron Hsu <byronhsu1230@gmail.com>
2025-04-23 01:46:01 -07:00
Yineng Zhang
fbb5f229d4 fix awq_dequantize import (#5669) 2025-04-23 01:36:26 -07:00
Yineng Zhang
15fabcc07f fix sgl-kernel unit tests (#5666) 2025-04-23 01:18:30 -07:00
Elfie Guo
e62c49557d [1/2] Add FP8 Blockscale MoE CUTLASS kernel for Blackwell (#5281) 2025-04-22 22:28:20 -07:00
fzyzcjy
71d1785f2d Remove unnecessary torch.full in DeepSeek (#5601) 2025-04-22 21:24:29 -07:00
Baizhou Zhang
3f87f83116 Fuse q_a_proj and kv_a_proj (#5619) 2025-04-22 20:35:08 -07:00
Baizhou Zhang
ce5412b62e Turn on DeepGemm By Default and Update Doc (#5628) 2025-04-22 16:10:08 -07:00
Yineng Zhang
7282ab741a fix: update bench_speculative (#5649) 2025-04-22 16:08:15 -07:00
HAI
b0feda090c Revert "Support aiter RMSNorm in AMD" (#5646) 2025-04-22 15:20:24 -07:00
Ke Bao
6b6e748775 Remove q concat in FA3 backend for DeepSeek decode (#5638) 2025-04-22 11:43:12 -07:00
JieXin Liang
917324862e [fix] reduce dp capture bs (#5634)
Co-authored-by: alcanerian <alcanerian@gmail.com>
2025-04-22 11:08:45 -07:00
lukec
2ed96c7a8a fix flashmla bug (#5272) 2025-04-22 10:36:23 -07:00
saltyfish66
2aa3f5e2d0 [feature] Add H20 fp8_w8a8 FusedMoE config for --n-share-experts-fusion=16 (#5641)
Co-authored-by: yuethe <yuethe@tencent.com>
2025-04-22 09:33:13 -07:00
lambert0312
76d17c7ecb Fix shared experts fusion error without quantization (#5632) 2025-04-22 09:22:26 -07:00
Connector Switch
70d040f904 [NFC] Remove duplicate compressed-tensors (#5640) 2025-04-22 09:10:25 -07:00
JieXin Liang
4418f599a5 Fix FA3 DeepSeek prefill performance regression (#5624)
Co-authored-by: ispobock <ispobaoke@gmail.com>
2025-04-22 01:41:41 -07:00
Yineng Zhang
04f2abcb34 fix: gemma 3 not use softcap (#5622) 2025-04-22 01:16:08 -07:00
JieXin Liang
506be6b892 [fix] fix compile_deep_gemm missing kv_b_proj (#5620) 2025-04-22 00:06:36 -07:00
JieXin Liang
2343d8df7d [fix] force use deepgemm in compile_deep_gemm (#5618) 2025-04-21 21:36:02 -07:00
Michael Yao
92bb64bc86 [Doc] Fix a 404 link to llama-405b (#5615)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
2025-04-21 20:39:37 -07:00
Ke Bao
11b23ae97b Remove extra copy in deepseek forward absorb (#5578)
Co-authored-by: saienduri <saimanas.enduri@amd.com>
2025-04-21 19:33:21 -07:00
Yineng Zhang
b9c87e781d chore: bump v0.4.5.post3 (#5611) 2025-04-21 18:16:20 -07:00
michael-amd
968ef51562 Support aiter RMSNorm in AMD (#5510)
Co-authored-by: JieXin Liang <Alcanderian@users.noreply.github.com>
2025-04-21 17:40:39 -07:00
Lianmin Zheng
1343200299 Clean up mem settings (#5610) 2025-04-21 17:19:00 -07:00
JieXin Liang
c2942907d5 [feature] enable pre compile jit deep_gemm (#5580) 2025-04-21 16:52:53 -07:00
Liangsheng Yin
e69a219074 Enhance GPU memory settings (#5604) 2025-04-21 15:15:00 -07:00
Byron Hsu
bf98d2e377 [PD] Support prefill overlap + Ensure no race condition (#5609) 2025-04-21 12:12:56 -07:00
Byron Hsu
e65b9f21e3 [PD] Support decode overlap schedule (#5608) 2025-04-21 12:06:16 -07:00
Trevor Morris
4dce1cc608 [PD] Add NIXL transfer backend (#5477) 2025-04-22 01:36:12 +08:00
Byron Hsu
deded17f38 [PD] Fix edge case and simplify large page size + chunked prefill (#5589) 2025-04-21 10:27:02 -07:00
shangmingc
f29a718f63 [PD] Fix generate endpoint of min_lb for PD (#5598)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-04-21 21:39:18 +08:00
Yongtong Wu
3f57b00a59 Support PD bootstrap fields on /v1/chat/completions endpoint (#5488) 2025-04-21 01:10:58 -07:00