kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-07 15:57:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
8,828 Commits 157 Branches 0 Tags
f44c63eef74d0e576d1031ca8a6cd21759e237f2
Commit Graph

5703 Commits

Author SHA1 Message Date
Hu Chong
f44c63eef7 [diffusion] chore: validate sampling params (#16677) 
Co-authored-by: root <root@huchong2-0.huchong2.podvm.svc.cluster.local>
 2026-01-12 16:00:10 +08:00
HuangJi
feb39f7768 [diffusion] model: Support TurboWan2.2-I2V SLA && add CI test for TurboWan (#16536) 2026-01-12 13:55:38 +08:00
Liangsheng Yin
5b7bed7ca4 Decouple grammar logic out of scheduler. (#16820) 2026-01-12 10:52:42 +08:00
chenxu140
38a88479c6 llama model and llama eagle3 model support dp-attn (#15268) 2026-01-12 08:54:56 +08:00
Liangsheng Yin
934ae89abe Tiny fix typo minxin -> mixin (#16908) 2026-01-12 00:36:45 +08:00
Yibo Cai
2f4a6addf3 [cpu/arm64] support run sglang on arm64 cpu (#14867) 2026-01-11 04:27:19 -08:00
Adarsh Shirawalmath
7b089ae4e0 [Diffusion] Docs for Diffusers backend (#16864) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-01-11 00:08:26 -08:00
Liangsheng Yin
09e2571e2e Clarify the meaning of cpu_group / entry_rank when dp + tp is enabled. (#16876) 2026-01-11 13:04:43 +08:00
Ratish P
c0248d6f37 [dpc]: unify DP controller load balancing and simplify dispatch logic (#16258) 2026-01-11 12:38:03 +08:00
Leoyzen
cf14feba4d Fix parallel tool call parsing bug when tool parameters contain arrays (#16345) 2026-01-10 19:31:38 -08:00
Mohammad Miadh Angkad
ff97814232 Tiny fix hicache kernel backend comparison (#16867) 
Signed-off-by: Mohammad Miadh Angkad <MAngkad.BSDSBA2027@aim.edu>
 2026-01-10 18:10:42 -08:00
DarkSharpness
d112f6a25b [Feature] Support JIT set kv cache (#16273) 2026-01-10 17:34:09 -08:00
Minglei Zhu
a2c2c09d7d [BugFix] fix gpt-oss-120b launch failure with --enable-piecewise-cuda-graph (#16757) 2026-01-11 09:19:59 +08:00
Yuwei An
2a9344d320 [tiny remove] remove torch_compile in parallel_state (#16865) 
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
 2026-01-10 16:04:25 -08:00
Qiaolin Yu
206db66f5c tiny refactor pcg split op registration (#16863) 2026-01-10 23:45:28 +08:00
WenhaoZhang
5c72be1e51 [diffusion] feat: support multiple LoRA adapters loading and application (#16667) 
Co-authored-by: niehen6174 <niehen.6174@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-01-10 23:32:45 +08:00
wxy
76d4881794 [diffusion] improve: apply tp optim to cross-attn for wan2.2 (#16788) 2026-01-10 21:25:59 +08:00
Yuan Luo
d1ec93e3ac Optimize layernorm_gated for Qwen3-Next (#16397) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-01-10 20:55:31 +08:00
WenhaoZhang
bdb76b34db [diffusion] fix: fix LoRA weight merging when using layerwise offload (#16737) 
Co-authored-by: niehen6174 <niehen.6174@gmail.com>
Co-authored-by: DavisTao <dwt614707404@163.com>
Co-authored-by: niehen6174 <nihen6174@gmail.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-01-10 20:17:35 +08:00
fzyzcjy
dae6a4092a Tiny add scheduler status logging (#16872) 2026-01-10 20:12:24 +08:00
fzyzcjy
a0899bdbd8 Fix log_decode_stats_every_iteration when having TP in attention (#16871) 2026-01-10 20:10:23 +08:00
fzyzcjy
641830c1c2 Tiny extract file logging utils (#16870) 2026-01-10 20:02:37 +08:00
YAMY
3fd88ea9b5 [MTP][spec_v2] Fix TRTLLM MLA backend crash in EAGLE draft_extend mode (#15790) 2026-01-10 19:58:23 +08:00
Yuwei An
145bd54f1b Piecewise Cuda Graph Memory Usage (#15927) 
Signed-off-by: Oasis-Git <ayw.sirius19@gmail.com>
 2026-01-10 19:29:13 +08:00
YAMY
2d088b85d9 [IDLE FORWARD][Indexer] Fix forward_idle bs mismatch issue in DeepseekV3.2's NSAIndexer (#15227) 2026-01-10 18:14:30 +08:00
lg(x)
3a8b44fe89 Update LoRA Weights via Tensor (#16226) 
Co-authored-by: PopSoda2002 <zhouhp.me@gmail.com>
 2026-01-10 17:36:43 +08:00
hlu1
aeb480c11f Add top-p to run_eval.py (#16844) 2026-01-10 17:10:37 +08:00
Baizhou Zhang
9fd2358cc2 Update Cutedsl version and pin cuda-python version (#16838) 2026-01-10 17:08:43 +08:00
Glen Liu
6327dff242 enhance LoRA tests and fix base model LoRA eviction in Scheduler (#16333) 2026-01-10 16:49:00 +08:00
Zhiqiang Xie
675acecec6 Attention backend selection bug fix for hicache (#16779) 
Co-authored-by: hxie <haiyong.xie@ustc.edu>
 2026-01-10 00:22:41 -08:00
Insideyyy
67b61a4e8d [Rework] Add SwapAB Optimization for triton fused_moe_kernel on SM90. (#16723) 2026-01-10 13:57:44 +08:00
Shifang Xu
d27f16f38a Fix EPLB + FP4 Quantization Compatibility Issue (#13715) 
Co-authored-by: Shu Wang <shuw@nvidia.com>
 2026-01-10 13:38:19 +08:00
fzyzcjy
c89949bbaf Tiny let soft watchdog cover initialization phase (#16853) 2026-01-10 13:20:08 +08:00
Ziang Li
20abaee26c [DSv32] Overlap indexer weights_proj during dual_stream decode (#16637) 
Co-authored-by: Ziang Li <ziangli@humansand.ai>
 2026-01-10 13:06:44 +08:00
fzyzcjy
32a569fb77 Tiny add CPU resource monitoring for overload diagnosis (#16852) 2026-01-10 12:48:18 +08:00
fzyzcjy
3ed3b7ef7c Tiny add routing key distribution metrics (#16847) 2026-01-10 12:06:40 +08:00
fzyzcjy
1f9d4795a9 Tiny add gauge histogram abstraction for engine and router (#16848) 2026-01-10 11:45:25 +08:00
Liangsheng Yin
e6d40bff81 Revert "feat: reduce constrained-decoding overhead in TP" (#16845) 2026-01-10 11:39:38 +08:00
若可
fbc128a32e fix(function_call): group batch decode by options instead of fallback (#16698) 
Co-authored-by: Muqi Li <muqi1029@gmail.com>
 2026-01-10 11:38:13 +08:00
Yinghai Lu
e91a717632 [llama] Allow passing tp_rank and tp_size into llama mlp (#16837) 2026-01-10 10:32:05 +08:00
fzyzcjy
1f0ea4f958 Add routing key based schedule policy (#16840) 2026-01-10 10:16:23 +08:00
fzyzcjy
15da3061bc Tiny pass routing key to scheduler processes (#16839) 2026-01-10 10:13:00 +08:00
fzyzcjy
6406a5969b Tiny support customizing prometheus buckets for prefill delayer (#16831) 2026-01-10 08:17:37 +08:00
fzyzcjy
cec19b56c6 Tiny add command line args for prefill delayer and unify names (#16830) 2026-01-10 07:54:25 +08:00
Yi Zhong
84ab32a2a0 Reduce some small cpu overhead in stream fetch (#16587) 
Signed-off-by: vincentzed <207368749+vincentzed@users.noreply.github.com>
 2026-01-09 21:53:06 +00:00
Leoyzen
8ef5b90528 Fix GLM-4.7 MoE Detector complex JSON Schema type parsing (#15753) 2026-01-10 01:21:10 +08:00
Raayan Dhar
76b3c698d6 feat: reduce constrained-decoding overhead in TP (#13947) 
Signed-off-by: Raayan Dhar raayan.dhar@gmail.com <raayan.dhar@gmail.com>
Signed-off-by: raayandhar <raayan.dhar@gmail.com>
 2026-01-10 00:38:32 +08:00
Hanming Lu
5dcff94791 [nemetron/mtp] fix nemotron mtp (#16275) 2026-01-09 23:22:21 +08:00
fzyzcjy
8eeffbe9aa Support token low usage watermark in prefill delayer (#16814) 2026-01-09 23:07:18 +08:00
fzyzcjy
7656d26737 Tiny enhance prefill delayer observability (#16812) 2026-01-09 22:51:16 +08:00