kvcache-ai/sglang
1
0
Fork 0
mirror of https://github.com/kvcache-ai/sglang.git synced 2026-07-08 16:27:09 +00:00
Code Issues Packages Projects Releases Wiki Activity
8,478 Commits 157 Branches 0 Tags
6bc5a52fd2d4807dcea21e822345fb5ea3e7bd4e
Commit Graph

5533 Commits

Author SHA1 Message Date
shengzhaotian
6bc5a52fd2 [NPU] Adapt qwen3-next W8A8 on NPU (#16164) 2026-01-03 19:41:20 +08:00
Mick
2c09de343e [diffusion] improve: skip loading vision module for text encoders (#16304) 2026-01-03 19:30:45 +08:00
Mick
38d48de93d [diffusion] CI: simplify warmup (#16303) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-01-03 18:09:38 +08:00
fzyzcjy
7f2fa2167b Tiny add --log-requests-target (#16338) 2026-01-03 17:28:27 +08:00
Xiaoyu Zhang
d0fb24ee7b [Diffusion] Flux2 tp support (#16219) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-01-03 17:02:27 +08:00
Siyuan Chen
9a414b164c [Performance] Optimze the performance of Qwen25VL (#15640) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2026-01-02 23:15:36 -08:00
Alison Shao
5b4f790200 [diffusion] CI: add CI validation for diffusion model downloads (#16311) 2026-01-03 14:12:45 +08:00
Teng Ma
bdde949619 [HiCache] Add PP Support with suffix pp rank (#15175) 
Co-authored-by: Xuchun Shang <xuchun.shang@gmail.com>
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2026-01-03 13:49:21 +08:00
fzyzcjy
9821fae5c6 Tiny add explanations to realtime token metric labels (#16009) 2026-01-03 12:36:55 +08:00
siyu
078d96213a [FEAT] optimize tensor zmq transfer for multimodal inputs (#13592) 
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
 2026-01-03 12:23:23 +08:00
b8zhong
74a166cb86 [Fix] Only add SM90 and SM100 to check for auto-enabling TRT Allreduce Fusion (#16283) 2026-01-03 11:43:17 +08:00
triple-mu
888e126ac9 [diffusion] comment: fix typo (#16257) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-01-03 11:42:04 +08:00
Baizhou Zhang
bb23a8fe77 [Tiny]Remove progress bar for fp8 ue8m0 quant when unneeded (#16177) 2026-01-03 10:54:12 +08:00
sunxxuns
8b869e326c [AMD] feat: add DLLM support for AMD GPUs with LLaDA2 testing (#15560) 2026-01-03 10:41:11 +08:00
Lianmin Zheng
62f73a8c81 [Auto Sync] Update engine.py (20260102) (#16317) 
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
 2026-01-02 17:29:40 -08:00
Ke Bao
7c1b4b1c4c Support swa allocator page size > 1 (#16296) 2026-01-03 08:49:47 +08:00
sunxxuns
30cfb687fa fixed amd multimodal CI failures caused by refactor in #15812 #15813 (#16287) 2026-01-02 14:55:42 -08:00
Baizhou Zhang
f07e76b229 Multiple refactors of DeepSeek V32 and context parallel (#16305) 2026-01-03 02:21:22 +08:00
Xiaoyu Zhang
1cfd2b2ded [diffusion] chore: remove redundant ulysses nccl warmup (#16301) 2026-01-03 00:19:35 +08:00
Yongfei Xu
0d244116d2 [DeepSeek v3.2] opt Context Parallelism: support fused moe, multi batch and fp8 kvcache (#13959) 2026-01-02 23:49:14 +08:00
Changyi Yang
0eae831797 [diffusion] fix: Increase text length from 256 to 1024 in Qwen-Image (#16248) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2026-01-02 23:25:31 +08:00
Ke Bao
c483a5f45f Tiny adjust hybrid swa handling (#16292) 2026-01-02 23:11:23 +08:00
Mick
f26f6c2c99 [diffusion] fix: make lora compatible with layerwise-offload (#16298) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-01-02 22:33:26 +08:00
roikoren755
b021332339 [NemotronH] Add latent MoE support (#16227) 
Signed-off-by: Roi Koren <roik@nvidia.com>
 2026-01-02 22:08:58 +08:00
Mick
5062537b67 [diffusion] feat: support lightweight e2e warmup for benchmarking (#16213) 2026-01-02 20:10:27 +08:00
Ke Bao
698629d1f2 Add swa page table to FA3 backend forward metadata (#16267) 2026-01-02 20:00:43 +08:00
Qiaolin Yu
dd93e4451c Support returning customized info (#16144) 2026-01-02 15:32:18 +08:00
Yuhao Yang
6c8587b5db [diffusion] fix: align negative prompt with official readme for new model (#16222) 2026-01-02 15:20:56 +08:00
Yinghai Lu
027042604d [distributed] Clean up MoE groups in destroy_model_parallel (#15345) 2026-01-02 14:45:14 +08:00
Xiaoyu Zhang
bd48ad5e6b [Diffusion] Fix broken ring_attention when use upstream fa3 (#16270) 2026-01-02 14:33:12 +08:00
fzyzcjy
749736ba95 Tiny fix single-gpu dumper and add tests for dumper (#16285) 2026-01-02 13:30:09 +08:00
Nan Jiang
7254986342 [VLM] feat: true on policy for vlm + fsdp (#14636) 
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
 2026-01-01 16:54:39 -08:00
DarkSharpness
f6f7af4068 [Refactor] Clean up custom op (#15995) 2026-01-01 21:41:56 +08:00
DarkSharpness
a3b1e8ef3d [Feature] add aligned_vector type for JIT kernel (#16162) 2026-01-01 21:40:05 +08:00
fzyzcjy
db499e1889 Tiny add filter, support duplications, add visualizations, fix error and robustness for dump comparator (#16262) 2026-01-01 17:47:00 +08:00
fzyzcjy
6cf3a6dd69 Support HTTP control for dumper (#16261) 2026-01-01 17:40:17 +08:00
fzyzcjy
90e24f5c31 Tiny add filter, dump dict, failable save to dumper (#16260) 2026-01-01 17:35:38 +08:00
Mick
21de3e1406 [diffusion] webui: tiny fix loading output image (#16251) 2026-01-01 14:34:49 +08:00
Lianmin Zheng
e4c1e441af Fix deprecation warning of sre_parse for python 3.13 (#16247) 2025-12-31 21:25:09 -08:00
1874.
e0e5084802 Fix parse args from file(#13911) (#14085) 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2026-01-01 11:37:33 +08:00
Yuan Luo
3a42c5e341 [VLM] Adopt jit qk_norm kernel in VLM (#16171) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-01-01 10:10:36 +08:00
Kangyan-Zhou
12b89e51d8 Add P90/99 e2e latency in bench_serving script (#16245) 2025-12-31 15:40:33 -08:00
Feng Su
57d2ba9203 SGLang Tracing: Supports propagating trace headers through sgl.Engine… (#15814) 
Signed-off-by: Feng Su <sufeng@linux.alibaba.com>
 2025-12-31 15:19:53 -08:00
ishandhanani
0500fea965 fix editable install (#16241) 2025-12-31 14:34:54 -08:00
Cheng Wan
2b461c15b4 Update logprob_start_len handling in scheduler (#16240) 2025-12-31 14:11:24 -08:00
siyu
abdf65d4f3 Fix OOM by offloading multimodal features to CPU after embedding (#16018) 2025-12-31 23:02:34 +08:00
Huaixin Chang
c1dfbc777b deprecate prefill-round-robin-balance (#16195) 
Signed-off-by: Chang Huaixin (OpenAnolis) <changhuaixin@linux.alibaba.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2025-12-31 22:25:33 +08:00
Muqi Li
2667c857a7 Fix DeepSeekV31's structural tag trigger (#13394) 2025-12-31 21:13:52 +08:00
Kangyan-Zhou
fc643ffbc9 Download missing shards in model weights files when not in CI (#16211) 2025-12-31 20:42:34 +08:00
Yuhao Yang
4280a18a13 [diffusion] CI: add test for cache-dit (#16204) 
Co-authored-by: Mick <mickjagger19@icloud.com>
 2025-12-31 19:58:10 +08:00