kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-07 07:47:25 +00:00
Code Issues Packages Projects Releases Wiki Activity
9,004 Commits 157 Branches 0 Tags
858a4d659b3e32bbb783a5782dc45f4653cc4e73
Commit Graph

5809 Commits

Author SHA1 Message Date
Gaoji Liu
858a4d659b support new qwen3_coder_detector (#16744) 
Co-authored-by: liugaoji.lgj <liugaoji.lgj@alibaba-inc.com>
 2026-01-18 21:16:27 -08:00
Lianmin Zheng
e619f53113 [Auto Sync] Update tokenizer_manager.py (20260119) (#17317) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2026-01-18 20:32:19 -08:00
Yongfei Xu
d2105d4abd [DeepSeek v3.2] Opt MTP decode cuda batch sizes and nsa implementation (#16961) 2026-01-19 11:54:11 +08:00
Lee Nau
84c8390514 Use dsv3 optimized routing fused_topk_deepseek instead of moe_fused_gate (#15347) 2026-01-19 11:50:16 +08:00
Baizhou Zhang
ea879c7739 [Minor] Correct sglang version when installing from source (#17315) 2026-01-18 19:36:16 -08:00
Shangming Cai
0227db8926 [PD] Optimize MHA models pp util calculation logic (#17306) 2026-01-19 11:23:15 +08:00
Glen Liu
ad1b4e4728 [Feature] overlap LoRA weight loading with compute (#15512) 2026-01-19 10:43:17 +08:00
Koushik Dutta
d3eafc7357 [GLM 4.7] Add RTX 6000 Pro aka sm120 (#17235) 
Co-authored-by: root <root@ubuntu-nvidia.localdomain>
 2026-01-18 13:33:19 -08:00
Jinyan Chen
e00b43442d [jit-kernel] Add CuTe DSL GDN Decode Kernel (#15631) 
Co-authored-by: Jinyan Chen <jinyanc@nvidia.com>
 2026-01-18 12:54:36 -08:00
Todobe
733de6be31 [NPU]Support GPT-OSS for NPU (#14197) 2026-01-19 04:13:41 +08:00
Jerry Ji
93433726eb [Refactor] Split out deepseek v2 weight loader function into mixin (#16649) 2026-01-19 00:41:59 +08:00
Xiaoyu Zhang
330605cc88 [Diffusion] Apply jit qk_norm to flux1 (#17296) 2026-01-19 00:28:36 +08:00
Ch3ngY1
bb6055b43c [Bugfix] Fix PD accuracy when MTP is not configured on the prefill node (#17212) 
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2026-01-18 23:37:58 +08:00
b8zhong
4df74eb576 [Refactor] Add -fp4-gemm-backend to replace SGLANG_FLASHINFER_FP4_GEMM_BACKEND (#16534) 
Co-authored-by: Vincent Zhong <207368749+vincentzed@users.noreply.github.com>
 2026-01-18 23:25:46 +08:00
Xinyuan Tong
2069050d3f fix: Handle multiple named chat templates in HuggingFace tokenizers (#17236) 
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2026-01-18 17:20:04 +08:00
YAMY
a45e0e5df4 [SPEC_V2] Enable cudagraph draft_extend for trtllm_mla_backend and Acclen Fix for DP under cudagraph mode (#16974) 2026-01-18 15:56:21 +08:00
Changyi Yang
8fd3399880 [diffusion] fix: set guidance_scale default to None (#17182) 2026-01-18 15:04:11 +08:00
Yuan Luo
6d29d8ab16 [VLM][Reland] Refactor load_mm_data to improve performance (#16152) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-01-18 14:11:17 +08:00
Ke Bao
e499258e97 Use swa radix cache and memory pool for gpt-oss model (#17261) 2026-01-18 13:47:07 +08:00
Mick
09491a9bcd cli: support sglang version (#17250) 2026-01-18 13:20:24 +08:00
Lancer
e486a4dac1 [diffusion] feat: support default 4-step inference for Flux2-Klein distilled models (#17225) 
Signed-off-by: Lancer <maruixiang6688@gmail.com>
 2026-01-18 10:15:50 +08:00
Hudson Xing
90399cbc07 fix(ci): recover from corrupted MMMU parquet cache (#17256) 2026-01-17 17:32:01 -08:00
Michael
53609e5e5b Revert "[Diffusion] Move diffusion time embedding to jit kernel" (#17257) 2026-01-17 21:29:22 +08:00
Zehuan Li
d2c863878c [DLLM] Implement initial dynamic batching for diffusion LLM (#14883) 2026-01-17 16:48:15 +08:00
Yi Zhang
737a1183d6 [BUGFIX] fix radix cache memory consumption to avoid OOM (#17191) 
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2026-01-17 16:47:37 +08:00
Mick
dc743fe4ba [diffusion] chore: clean srt imports (#17252) 2026-01-17 15:47:49 +08:00
Nan Jiang
dd99f818e0 fix: fix regression and unclear pattern (#16561) 2026-01-16 23:21:42 -08:00
Hudson Xing
8ce64aa155 fix(ci): skip offline mode for LoRA scenarios (#17248) 2026-01-16 23:06:20 -08:00
Mick
eb768189ee [diffusion] doc: add instruction for adding performance baseline of new model (#17249) 2026-01-17 12:24:59 +08:00
Xiaoyu Zhang
2cdd4370bc [Diffusion] Move diffusion time embedding to jit kernel (#16879) 2026-01-17 12:21:22 +08:00
siyu
e18e0057a4 Add an env var to allow transferring small metadata via TCP for PD (#16951) 2026-01-16 18:32:22 -08:00
Stefan He
43779f27b7 Disable PCG for draft worker (#16354) 2026-01-17 09:56:56 +08:00
Baizhou Zhang
8b9e9357fe [2/n] deepseek_v2.py Refactor: Migrate MHA forward method in deepseek_v2.py (#16817) 2026-01-17 09:36:25 +08:00
b8zhong
d36f6f043c [Fix] flashinfer_trtllm intermediate_size assertion with Qwen3 + TP=8 (#16824) 2026-01-17 09:24:05 +08:00
Lingjun Wen
7f8353aff3 [BugFix]: Fix sglang.bench_one_batch (#16925) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2026-01-16 13:15:34 -08:00
Baizhou Zhang
a04675892e Update flashinfer to 0.6.1 (#15551) 2026-01-17 00:48:30 +08:00
Yongfei Xu
82a1b645ba [DeepSeek V3.1/V3.2] Optimize fused moe configs for H20 & H20-3E based on swapab (#17133) 2026-01-17 00:10:52 +08:00
billishyahao
6f10e17b4a [bugfix] fix qwen3-next alt_stream none issue (#17016) 2026-01-16 22:40:25 +08:00
Nicolas Castet
9d8bbd4223 Add clear error message when OOM with symmetric memory (#17038) 2026-01-16 20:44:37 +08:00
Raghav Ravishankar
daea51385d Add AFMoE model implementation (#13216) 2026-01-16 20:35:42 +08:00
StonyPort
3355b6e21b feat: add request queued timeout (#17143) 
Co-authored-by: qiuxuan.lzw <qiuxuan.lzw@alibaba-inc.com>
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
 2026-01-16 17:55:09 +08:00
R0CKSTAR
a1dd3d48ac [diffusion] hardware: support diffusion (single GPU, 3/N) (#17105) 
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
 2026-01-16 17:01:09 +08:00
Zhiqiang Xie
d9ed80b9f1 fix AMD CI failure of NUMA binding (#17184) 2026-01-16 00:21:04 -08:00
Adarsh Shirawalmath
7c39ea68f3 [diffusion] model: support flux Klein (#17173) 2026-01-16 16:16:17 +08:00
YAMY
daa4841e86 [ConfigArgumentMerger] Improve ConfigArgumentMerger compatibility with external callers (#17051) 2026-01-16 15:32:42 +08:00
Hudson Xing
21ee597e4a ci: enable offline mode when local cache is complete to avoid HF Hub … (#16121) 2026-01-15 20:15:33 -08:00
Xiaoyu Zhang
6ee970a365 [Diffusion] Hot fix broken output_path default value (#17180) 2026-01-16 12:14:09 +08:00
shuwenn
8ec160ed46 feature: support uvicorn access log filter(disable logging /metrics) (#15513) 2026-01-15 20:00:06 -08:00
YAMY
2740ed1ae7 [eval] GSM8k support for run_eval (#17041) 2026-01-16 11:10:17 +08:00
Lianmin Zheng
e7dc85c50b Fix grammar sync across TP ranks (#17100) 
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2026-01-15 18:38:01 -08:00