Commit Graph

3687 Commits

Author SHA1 Message Date
JieXin Liang
ab1a4fa5cb [fix] fix cutlass_mla_backend with cuda_graph and add sm_scale for sgl-kernel cutlass_mla (#7184) 2025-06-14 12:45:41 -07:00
JieXin Liang
ed54bf9d19 [fix] fix dsv3 weight loader tqdm and simplify shared experts fusion (#7181) 2025-06-14 11:56:29 -07:00
fzyzcjy
b57d87c297 Fix shared experts fusion + weight requant (#7177) 2025-06-14 02:35:18 -07:00
Lifu Huang
98538822d5 Add Phi-4-mm to supported VLM supported model list. (#7178) 2025-06-13 23:17:40 -07:00
Lianmin Zheng
f47a1b1d0f Increase timeout in test/srt/test_disaggregation.py (#7175) 2025-06-13 23:12:14 -07:00
fzyzcjy
93cec4335f Support new DeepGEMM (#7172) 2025-06-13 23:00:17 -07:00
Lianmin Zheng
ba589b88fc Improve test cases for eagle infer (#7173) 2025-06-13 22:25:13 -07:00
Jinn
50876abc47 Add test for refactored openai server (#7161) 2025-06-13 20:42:57 -07:00
fzyzcjy
b4c41f7276 Refactor DeepGEMM integration (#7150) 2025-06-13 20:41:03 -07:00
fzyzcjy
8b8f2e7463 Support new DeepGEMM input format in silu_and_mul_masked_post_quant_fwd (#7153) 2025-06-13 20:40:24 -07:00
Lianmin Zheng
0fc3d992bb Split the eagle test into two files (#7170) 2025-06-13 20:14:26 -07:00
Lianmin Zheng
be2d985df8 Minor style change of triton backend (#7165) 2025-06-13 16:01:23 -07:00
fzyzcjy
5b1afa7814 Re-quantize DeepSeek model weights to support DeepGEMM new input format (#7156) 2025-06-13 15:57:45 -07:00
fzyzcjy
c49c1d9226 Remove 200us slow concat kernel (part 2: srt) (#7020) 2025-06-13 15:19:31 -07:00
fzyzcjy
0f1dfa1efe Tiny add sanity checks for DeepGEMM inputs (#7157) 2025-06-13 14:36:27 -07:00
fzyzcjy
e3ec6bf4b6 Minor speed up block_quant_dequant (#6814) 2025-06-13 14:32:46 -07:00
fzyzcjy
b04df75acd Fix DeepEP error in some environments (#7154) 2025-06-13 14:27:25 -07:00
fzyzcjy
bec3e48402 Support new DeepGEMM format in per token group quant (part 2: srt) (#7155) 2025-06-13 14:25:40 -07:00
Yineng Zhang
8ab7d93c2e chore: bump v0.1.8.post1 (#7152) 2025-06-13 03:14:26 -07:00
fzyzcjy
5c66c4424f Support new DeepGEMM format in per token group quant (#7146) 2025-06-13 02:00:22 -07:00
fzyzcjy
aa46ed34d2 Remove 200us slow concat kernel (part 1: kernel) (#7145) 2025-06-13 01:58:29 -07:00
pansicheng
2f4ec752bc filter by num_hidden_layers (#7056) 2025-06-13 00:53:09 -07:00
fzyzcjy
da47621ccc Minor speedup topk postprocessing (#7058) 2025-06-13 00:50:18 -07:00
Binyao Jiang
22a6b9fc05 Remove unnecessary metadata_expand.max_seq_len_k operations in fa3 to… (#7140) 2025-06-12 23:25:52 -07:00
fzyzcjy
b02df20a8d Minor add utility to read expert distribution recorder output (#7134) 2025-06-12 16:50:05 -07:00
Povilas Kanapickas
bd7cfbd2f8 [Fix] Reduce busy polling when scheduler is idle (#6026) 2025-06-12 14:58:22 -07:00
sogalin
4b9971e401 Add gfx950 support for sgl-kernel. (#7092)
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: Yineng Zhang <me@zhyncs.com>
2025-06-12 11:07:48 -07:00
Lianmin Zheng
dcc79d325b Update CODEOWNERS (#7126) 2025-06-12 02:12:49 -07:00
Yineng Zhang
7046e0fab7 feat: update blackwell setup (#7119) 2025-06-12 01:54:40 -07:00
Liangsheng Yin
930746d93c Improve log status (#7115) 2025-06-12 14:38:24 +08:00
Yuan Luo
84727a5139 [sgl-kernel] Add cuda kernel for moe_ep_silu_and_mul (#6919)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-06-11 20:43:08 -07:00
Quanfeng Li
ef32677444 Fix positional argument (#7093) 2025-06-11 18:31:13 -07:00
Lifu Huang
021f76e4f4 [Perf] Refactor LoRAManager to eliminate stream syncs and redundant computations (#6994) 2025-06-11 16:18:57 -07:00
Faradawn Yang
777688b892 [feat]: Emit fixed-size KV blocks events (#6824) 2025-06-11 13:07:58 -07:00
Neo
0ca594eda9 [FIX]remove redundant code in logits_processor.py (#7079) 2025-06-11 11:49:30 -07:00
Zijian
31d6dee5c4 Support VILA models (#6106) 2025-06-11 11:47:25 -07:00
sogalin
02543b545c Fix misusing the "_is_cuda". (#7091) 2025-06-11 11:21:31 -07:00
Baizhou Zhang
25a6a9aa22 Fix circular import in test_prefix_chunk_info.py (#7097) 2025-06-11 10:57:45 -07:00
Mick
83d87685c5 vlm: adapt internvl to VisionAttention (#6870) 2025-06-11 01:16:04 -07:00
Baizhou Zhang
2a5f0100e0 Fix GGuf and add back test_gguf.py (#7067) 2025-06-10 21:07:20 -07:00
Lianmin Zheng
dbdf76ca98 Clean up docs for server args and sampling parameters (generated by grok) (#7076) 2025-06-10 19:55:42 -07:00
Ximingwang-09
f2a75a66c4 update doc (#7046)
Co-authored-by: ximing.wxm <ximing.wxm@antgroup.com>
2025-06-11 10:02:01 +08:00
Lianmin Zheng
6b12d6a8d5 Simplify the heuristics for setting --mem-fraction-static (#7054) 2025-06-10 19:01:39 -07:00
Lianmin Zheng
0f218731e3 Do not run frontend_reasoning.ipynb to reduce the CI load (#7073) 2025-06-10 17:15:31 -07:00
Yudi Xue
14c18d25df Frontend language separate reasoning support (#6031) 2025-06-10 17:11:29 -07:00
Lianmin Zheng
90bd3e32d6 Improve perf tuning docs (#7071) 2025-06-10 16:55:04 -07:00
Brayden Zhong
ca9291181d [Feature] Add Logit Bias (#6579)
Co-authored-by: Cinjon Resnick <cinjon.resnick@gmail.com>
2025-06-10 15:39:25 -07:00
Yineng Zhang
344adb00ec fix arm sgl-kernel link issue (#7066) 2025-06-10 15:23:22 -07:00
kyle-pena-kuzco
b56de8f943 Open AI API hidden states (#6716) 2025-06-10 14:37:29 -07:00
Yineng Zhang
ce5ee3bdf0 chore: update dev docker (#7064) 2025-06-10 12:57:58 -07:00