Commit Graph

4977 Commits

Author SHA1 Message Date
Lianmin Zheng
2dae104dca Minor cleanup of fa3 backend (#6999) 2025-06-10 03:58:44 -07:00
Yineng Zhang
cef6655b26 fix 24.12 docker (#7045) 2025-06-10 02:43:22 -07:00
Swipe4057
27196d4148 [Docker] Upgrading base image from 24.04 to 24.12 (#7043) 2025-06-10 02:23:05 -07:00
Lianmin Zheng
bb185b0e92 Update README.md (#7040) 2025-06-10 01:59:14 -07:00
Yineng Zhang
4f723edd3b chore: bump v0.4.7 (#7038) 2025-06-10 01:56:20 -07:00
YanbingJiang
fcde67b016 CPU: map changes from developing branch in sgl-kernel (#6833)
Co-authored-by: mingfeima <mingfei.ma@intel.com>
2025-06-10 01:08:15 -07:00
yudian0504
81372f3bef Fix fused_moe triton configs (#7029) 2025-06-09 23:23:03 -07:00
Arthur Cheng
baa6624d7c [CI] Add CI workflow for sgl-router docker build (#7027) 2025-06-09 23:16:44 -07:00
Byron Hsu
c2b16795b5 Add decode req pool (#6980) 2025-06-09 21:23:36 -07:00
fzyzcjy
f6ebba537a Support both approximate and exact expert distribution collection (#6964) 2025-06-09 20:56:17 -07:00
Baizhou Zhang
6716b41786 Update default settings for blackwell (#7023) 2025-06-09 20:37:47 -07:00
Yineng Zhang
1c8b42c84c chore: update pr test xeon (#7018) 2025-06-09 17:36:25 -07:00
Qiaolin Yu
f20f70003d Fix torch version in blackwell dockerfile (#7017) 2025-06-09 17:06:50 -07:00
Emmanuel Ferdman
f40942ad63 Migrate to assertEqual (#6741)
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
2025-06-09 16:47:39 -07:00
Lianmin Zheng
dc0705a504 Simplify prepare_extend_after_decode (#6987) 2025-06-09 16:39:21 -07:00
Wenxuan Tan
a968c888c0 Fix torchvision version for Blackwell (#7015) 2025-06-09 15:50:19 -07:00
Baizhou Zhang
a979daac3b Fallback to lower triton version for unfound fused moe configs (#7013) 2025-06-09 15:41:03 -07:00
ishandhanani
f1569876d5 feat: add direct routing strategy to DP worker (#6884) 2025-06-09 11:44:05 -07:00
Sai Enduri
3465d7ae78 Update amd nightly models CI. (#6992) 2025-06-09 10:54:08 -07:00
fzyzcjy
e58423b2b9 Fix cutlass MLA gets almost zero accuracy (#6998) 2025-06-09 10:16:29 -07:00
Yineng Zhang
7059ae16fb chore: update pr test xeon (#7008) 2025-06-09 10:08:44 -07:00
Yineng Zhang
51d9a597f9 cleanup tmp dir (#7007) 2025-06-09 09:26:04 -07:00
Yineng Zhang
56ccd3c22c chore: upgrade flashinfer v0.2.6.post1 jit (#6958)
Co-authored-by: alcanderian <alcanderian@gmail.com>
Co-authored-by: Qiaolin Yu <qy254@cornell.edu>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
2025-06-09 09:22:39 -07:00
Yueyang Pan
98c00a2df1 Fix torch profiler bugs for bench_offline_throughput.py (#6557) 2025-06-09 20:33:41 +08:00
Pan Lyu
451ffe74d9 support qwen3 emebedding (#6990) 2025-06-09 01:32:49 -07:00
Lifu Huang
b1e5a33ae3 Eliminate stream sync to speed up LoRA batch init (#6960) 2025-06-09 00:22:45 -07:00
Lianmin Zheng
9d5fa68b90 Use torch.compile to fuse flash attention decode metadata preparation (#6973) 2025-06-08 23:05:40 -07:00
Sai Enduri
2c18642502 Enable more unit tests for AMD CI. (#6983) 2025-06-08 19:41:55 -07:00
JieXin Liang
18efb5e8e0 [perf][sgl-kernel] extend cutlass_mla_decode to support num_head < 128 (#6929) 2025-06-08 19:37:34 -07:00
fzyzcjy
de1350ea20 Minor remove one kernel for DeepSeek (#6977) 2025-06-08 17:41:35 -07:00
fzyzcjy
86fe943bc3 Fix expert distribution dumping causes OOM (#6967) 2025-06-08 17:41:14 -07:00
Lianmin Zheng
9ecb18568b Fix triton sliding window test case (#6981) 2025-06-08 17:20:46 -07:00
Ke Bao
cc74499d51 Fix draft extend ut stability with flush cache (#6979) 2025-06-08 17:09:32 -07:00
Lianmin Zheng
0c1f03a23d Sync cuda graph runners (#6976) 2025-06-08 16:12:25 -07:00
Xiaoyu Zhang
3712abfaf9 Fuse routed scaling factor in deepseek (#6970) 2025-06-08 15:24:24 -07:00
Baizhou Zhang
971a0dfa32 Extend cuda graph capture bs for B200 (#6937) 2025-06-08 05:13:22 -07:00
fzyzcjy
2fc1299562 Remove unnecessary kernels of num_token_non_padded (#6965) 2025-06-08 05:09:17 -07:00
Lianmin Zheng
20d3ad3b58 Fix CI and triton moe Configs (#6974) 2025-06-08 05:06:46 -07:00
Xiaoyu Zhang
fa3592cfeb rebase h20 fused_moe config (#6966) 2025-06-08 05:01:34 -07:00
Lianmin Zheng
608668e143 Slightly improve the sampler to skip unnecessary steps (#6956) 2025-06-08 03:18:54 -07:00
Yineng Zhang
6c0a48282a chore: bump sgl-kernel v0.1.7 (#6963) 2025-06-08 02:43:15 -07:00
Hubert Lu
4740288303 [AMD] Add more tests to per-commit-amd (#6926) 2025-06-08 01:08:37 -07:00
Yineng Zhang
1fb76ebb93 Revert "Fuse routed scaling factor in topk_reduce kernel (#6220)" (#6968) 2025-06-07 21:02:49 -07:00
Pavani Majety
c2c4f57f63 [DeepseekR1-FP4] Add Support for nvidia/DeepSeekR1-FP4 model (#6853)
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
2025-06-07 17:24:35 -07:00
Yineng Zhang
23881fa60c chore: upgrade sgl-kernel v0.1.6.post1 (#6957) 2025-06-07 17:18:55 -07:00
Yineng Zhang
8db3ac55a9 chore: bump sgl-kernel v0.1.6.post1 (#6955) 2025-06-07 15:25:46 -07:00
Elfie Guo
3e56f557fd Add a CUDA kernel for fusing mapping and weighted sum for MoE. (#6916)
Co-authored-by: Elfie Guo <elfiegxf@gmail.com>
2025-06-07 15:24:39 -07:00
Xu Wenqing
62fec60d81 Add H20 fused MoE kernel tuning configs for DeepSeek-R1/V3 (#6885)
Signed-off-by: Xu Wenqing <xuwq1993@qq.com>
2025-06-07 15:17:34 -07:00
JieXin Liang
e7759778e5 [misc] add is_cpu() (#6950) 2025-06-07 15:13:45 -07:00
Sai Enduri
77e928d00e Update server timeout time in AMD CI. (#6953) 2025-06-07 15:10:27 -07:00