Commit Graph

1723 Commits

Author SHA1 Message Date
Qiaolin Yu
9fdc6d6abc Fix the lora adapter when lora path is none (#4799)
Co-authored-by: Beichen Ma <mabeichen12@gmail.com>
2025-03-27 21:03:08 -07:00
XinyuanTong
42a45df043 [Fix] self.worker assignment in TpModelWorker and refactor references (#4788)
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
2025-03-27 20:28:38 -07:00
Jon Durbin
04eb6062e4 Include context length in /v1/models response. (#4809) 2025-03-27 20:23:18 -07:00
Brayden Zhong
e84f4ba0ab [Misc] Fix issues reported by torchfix (#4837) 2025-03-27 20:10:32 -07:00
Kebe
10a9ab7b07 Fix error due to CustomAllreduce setup failure (#4815)
Signed-off-by: Kebe <mail@kebe7jun.com>
2025-03-27 18:52:10 -07:00
Junrong Lin
bb0fd749a6 [Fix] Add compressed_tensors as deps (#4819) 2025-03-27 18:08:24 -07:00
tarinkk
7f19e083c1 Support (1 <= dp < tp) in the dp attention in DeepEP (#4770)
Co-authored-by: Cheng Wan <cwan39@gatech.edu>
2025-03-27 17:09:35 -07:00
Juwan Yoo
188105a21b deps: lazy import optional dependencies gguf and torchvision (#4826) 2025-03-27 14:35:36 -07:00
Yineng Zhang
bbab97a6a8 add partial_json_parser and einops (#4827) 2025-03-27 13:24:54 -07:00
Juwan Yoo
0bc0bf5734 gemma3: impl get_attention_sliding_window_size for attn init (#4823) 2025-03-27 10:43:58 -07:00
AinL
17000d2b3a Remove Unintended Capture Batch Sizes in AMD HIP Graph Runner (#4638) 2025-03-27 08:41:33 -07:00
strgrb
668ecc6c5b Fix ut mla-test-1-gpu-amd (#4813)
Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
2025-03-27 08:27:51 -07:00
strgrb
886fcbdd09 Use apply_rope_with_cos_sin_cache_inplace for DeepSeek (#4764)
Co-authored-by: Zhang Kaihong <zhangkaihong.zkh@alibaba-inc.com>
2025-03-27 01:45:37 -07:00
Stefan He
1b9175cb23 [FA3 Attn Backend] Remove Unnecessary Device Sync for FA3 (#4745)
Co-authored-by: Yubo Wang <yubowang2019@gmail.com>
2025-03-27 00:45:11 -07:00
fzyzcjy
92bb49a7f9 Patch PyTorch's bug that cross-process tensor transfer will lead to wrong device (#4565) 2025-03-27 00:22:33 -07:00
Yineng Zhang
6f5cc5eb05 update xgrammar 0.1.17 (#4804) 2025-03-27 00:21:59 -07:00
Pan Lyu
c913ed4046 support clip embedding model (#4506) 2025-03-27 00:18:15 -07:00
Xihuai Wang
1afe3d0798 Align finish reason and stream mode in openai api (#4388) 2025-03-27 00:16:52 -07:00
laixin
ae25d36dc6 [3/3] fix dsv3 awq issue (#4719)
Co-authored-by: AniZpZ <aniz1905@gmail.com>
2025-03-26 23:13:43 -07:00
Yineng Zhang
1099f6c974 bump v0.4.4.post2 (#4669) 2025-03-26 19:58:00 -07:00
Xiaoyu Zhang
04e3ff6975 Support compressed tensors fp8w8a8 (#4743) 2025-03-26 13:21:25 -07:00
Yi Pan
45fdf1f7f3 Fix shared memory OOM on sm86 GPUs. (#4797) 2025-03-26 10:41:53 -07:00
Kebe
d89c0e4b7e Use metadata to detect version of package (#4782)
Signed-off-by: Kebe <mail@kebe7jun.com>
2025-03-26 00:41:43 -07:00
fzyzcjy
fa3c9e0668 Fix popen_launch_server wait for 20 minutes when child process exits (#4777) 2025-03-26 00:32:19 -07:00
Cheng Wan
0d658ac3df Support recording experts workload in QWen2-MoE (#4775) 2025-03-26 00:29:57 -07:00
Thysrael
ced35a0649 fix(typo): fix reply to replay in base_attn_backend.py (#4784) 2025-03-26 00:19:12 -07:00
fzyzcjy
26f07294f1 Warn users when release_memory_occupation is called without memory saver enabled (#4566) 2025-03-26 00:18:14 -07:00
Baizhou Zhang
34e07a65f1 [Fix] Fix unexpected idx bug of Phi-3-small (#4728) 2025-03-25 21:33:48 -07:00
fzyzcjy
15ddd84322 Add retry for flaky tests in CI (#4755) 2025-03-25 16:53:12 -07:00
fzyzcjy
52029bd1e3 Fix warmup error when dp=1 (#4753) 2025-03-25 02:01:21 -07:00
fzyzcjy
eb934bdf3b Fix test_expert_distribution failure (#4752) 2025-03-25 01:17:03 -07:00
DarkSharpness
ac3fae8445 [Feature] Support "strict" in function calling (#4310) 2025-03-24 22:15:25 -07:00
yuhsaun-t
199bb01d00 Add endpoints to dump selected expert ids (#4435)
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
2025-03-24 21:34:19 -07:00
fzyzcjy
6b7038babd Speedup warmup when DP > 1 (#4695) 2025-03-24 21:08:05 -07:00
lukec
57eec0bfbc fix FlashMLA cudagraph config (#4691)
Co-authored-by: yinfan98 <1106310035@qq.com>
2025-03-24 21:06:58 -07:00
fzyzcjy
f01b092519 Super tiny fix typo (#4738) 2025-03-24 21:05:45 -07:00
Mick
1e86457c90 model: Minicpmo (#3023) 2025-03-24 20:08:40 -07:00
Ximingwang-09
22c3702e1e [Model] Support Qwen2ForSequenceClassification (#4609)
Co-authored-by: ximing.wxm <ximing.wxm@antgroup.com>
2025-03-24 19:13:44 -07:00
Stefan He
4c584fc632 Fix circular imports in gptq.py and unblock test explorer (#4736) 2025-03-24 18:07:08 -07:00
Ke Bao
77cf771ebe Fix EAGLE3 for llama3.3 70b (#4716) 2025-03-24 17:31:19 -07:00
Xuchun Shang
8154de5a32 [PD] Remove invalid parameter (#4721)
Signed-off-by: Xuchun Shang <xuchun.shang@linux.alibaba.com>
2025-03-24 13:14:16 -07:00
Yineng Zhang
c11cfda07b update pyproject (#4731) 2025-03-24 09:50:28 -07:00
Yuhong Guo
64edeb798f Support dynamic version name in sglang's pyproject.toml (#4720) 2025-03-24 08:56:31 -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