EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity
2,673 Commits 8 Branches 0 Tags
8e10fec9a8c80216307adb64241cdb7a5fa48d36
Commit Graph

1770 Commits

Author SHA1 Message Date
fzyzcjy
8e10fec9a8 Small refactor DeepEPMode to clean up code a bit (#4992) 2025-04-03 02:56:44 -07:00
Baizhou Zhang
e8999b13b7 Replace enable_flashinfer_mla argument with attention_backend (#5005) 2025-04-03 02:53:58 -07:00
saltyfish66
e41549c3d6 fix: fix illegal cuda memory access at fused_moe_kernel (#4727) 
Co-authored-by: yuethe <yuethe@tencent.com>
 2025-04-03 00:07:32 -07:00
Kaiyu Yang
31da75abed Update tokenizer_manager.py (#5008) 2025-04-02 13:56:19 -07:00
Qingquan Song
e983e43248 Add Eagle Speculative Decoding to FA3 Backend (#4951) 
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: zcnrex <zcnrex@gmail.com>
 2025-04-02 13:09:02 -07:00
Xiaoyu Zhang
e9c6ce461d sgl scaled_fp8_quant support output padding (#4861) 2025-04-02 23:53:57 +08:00
Zhiqiang Xie
3fadc64793 bug fix for hicache host eviction (#4989) 2025-04-02 00:33:50 -07:00
Zhiqiang Xie
e119f04215 Large page size aligned hierarchical caching (#4581) 2025-04-01 22:38:15 -07:00
XinyuanTong
9eb49e878b [VLM RLHF] Take Image input for verl vlm rollout (#4915) 
Signed-off-by: Xinyuan Tong <justinning0323@outlook.com>
Co-authored-by: GeLee <leege233@gmail.com>
 2025-04-01 20:03:17 -07:00
Zhiqiang Xie
12047f5e94 Prevent memory leak of retract_decode when page_size > 1 (#4977) 2025-04-01 15:30:45 -07:00
Yineng Zhang
fda6bb78da update bench_serving (#4958) 2025-04-01 15:10:56 -07:00
Jinyan Chen
23c764b18a [Feature] Support DeepEP Low Latency (#4767) 
Co-authored-by: sleepcoo <sleepcoo@gmail.com>
Co-authored-by: laixinn <xielx@shanghaitech.edu.cn>
Co-authored-by: ch-wan <cwan39@gatech.edu>
 2025-04-01 09:23:25 -07:00
Yuhong Guo
87fafa0105 Revert PR 4764 & 4813 related to R1 RoPE (#4959) 2025-03-31 20:56:58 -07:00
Yineng Zhang
1c63e79756 use fa3 in sgl-kernel (#4954) 2025-03-31 16:14:49 -07:00
Mick
5cb552b1d4 refactor: multimodal data (#4754) 2025-03-31 09:57:51 -07:00
JieXin Liang
51ac297ace [feat] interface for platforms abstraction (#4928) 2025-03-31 00:04:21 -07:00
Zhiqiang Xie
a169b9f813 Fix oom error for large page size (#4913) 
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
 2025-03-30 21:34:21 -07:00
Baizhou Zhang
4a63bc32b7 [Fix] Add torch compile for torch.clamp back (#4936) 2025-03-30 20:46:07 -07:00
fzyzcjy
a303325fdb Fix DeepSeek bug causing 2.2% MMLU drop when TP!=DP (#4883) 
Co-authored-by: ch-wan <cwan39@gatech.edu>
 2025-03-30 20:10:21 -07:00
Baizhou Zhang
e62d60fe6d [Fix] avoid stream sync and torch compile in prefill for fa3 backend (#4932) 2025-03-30 13:53:44 -07:00
SEPLOS
032f8faaab Fix sglang frontend's incorrect dependency on torch (#4931) 2025-03-30 13:00:24 -07:00
Lianmin Zheng
9adf178cc2 Fix 2-gpu CI test and suppress some warnings (#4930) 2025-03-30 12:51:44 -07:00
Lianmin Zheng
4ede6770cd Fix retract for page size > 1 (#4914) 2025-03-30 02:57:15 -07:00
Lianmin Zheng
b26bc86b36 Support page size > 1 + eagle (#4908) 2025-03-30 00:46:23 -07:00
fzyzcjy
8690c40bb0 Improve stack trace of retry errors (#4845) 2025-03-29 08:21:31 -07:00
fzyzcjy
b1cfb4e972 Fix BadRequestError wrong arguments and remove openai dependency (#4882) 2025-03-29 08:16:21 -07:00
Yineng Zhang
19e96e5923 bump v0.4.4.post3 (#4878) 2025-03-28 23:21:24 -07:00
Yineng Zhang
d8a136a113 upgrade sgl-kernel 0.0.5.post4 (#4873) 2025-03-28 19:48:56 -07:00
Baizhou Zhang
20c90be23d [Feature] Support FA3 backend for MLA (#4831) 2025-03-28 18:30:14 -07:00
Qingquan Song
044c315970 Make torch compile configurable for biased_grouped_topk (#4749) 2025-03-28 10:57:52 -07:00
Fr4nk1in
c483377ed7 Fix wrong variable name when stopping memory profile (#4772) 2025-03-28 10:35:02 -07:00
Lianmin Zheng
74e0ac1dbd Clean up import vllm in quantization/__init__.py (#4834) 2025-03-28 10:34:10 -07:00
chaobo jia
ef9a378a20 [Feature] add multi-rank support for Lora (#4492) 
Co-authored-by: rudy152 <czh1137892874@gmail.com>
 2025-03-28 09:38:44 -07:00
Qingquan Song
6ffb6bd47a Fix fa3 cuda graph page_size > 1 precision and page_size=1 speed (#4855) 2025-03-28 01:35:59 -07:00
Lianmin Zheng
47e6628aae Fix CI tests (#4853) 2025-03-28 00:28:35 -07:00
fzyzcjy
8c04f0f2e1 Support with_stack and record_shapes in profiler (#4740) 
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
 2025-03-27 23:01:42 -07:00
fzyzcjy
265e756494 Super tiny remove unused code (#4750) 2025-03-27 22:32:14 -07:00
fzyzcjy
d3f71f5e19 Fix torch.cuda.MemPool() internal assertion failure (#4687) 
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
 2025-03-27 22:29:36 -07:00
Kebe
e0166f8ab4 Remove empty tool function name (#4704) 
Signed-off-by: Kebe <mail@kebe7jun.com>
 2025-03-27 22:23:30 -07:00
fzyzcjy
53a2c3b466 Support controlling nsys start and end range programmatically (#4688) 2025-03-27 22:21:13 -07:00
BroadbentJim
550586ef42 fix: Inappropriate lack of Optional type on OpenAI ChatCompletionRequest (#4681) 2025-03-27 22:19:05 -07:00
fzyzcjy
cf29fe9e78 Fix Engine error when enabling DP attention (#4648) 2025-03-27 22:17:30 -07:00
Stefan He
26c0f13126 Support Page Size > 1 for FA3 (#4832) 
Co-authored-by: Qingquan Song <ustcsqq@gmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
 2025-03-27 22:07:14 -07:00
rongfu.leng
f9970bd1af fix: when use SGLANG_PORT this env,port is str (#4528) 
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
 2025-03-27 21:46:06 -07:00
lambert0312
2e0f94ab79 [Fix] fix output_top_logprobs is not exist (#4597) 2025-03-27 21:45:57 -07:00
Vincent
e2e2ab70e0 IPv6 support (#3949) 
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
 2025-03-27 21:42:13 -07:00
Jiaqi
72031173e4 fix: fix typo of comments in w8a8_fp8.py (#4843) 2025-03-27 21:06:47 -07:00
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