chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity
8,896 Commits 1 Branch 0 Tags
424a3800773501d79daa06fbf6c8b83e2fdfe4ac
Commit Graph

8896 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Артем Савкин
424a380077 [NPU] NPU quantization refactoring & more quantization formats support (#14504) 
Co-authored-by: TamirBaydasov <mr.jeijy@gmail.com>
Co-authored-by: Tamir Baydasov <41994229+TamirBaydasov@users.noreply.github.com>
Co-authored-by: Савкин Артем <savkinartem@MacBook-Air-Viktoria.local>
Co-authored-by: Edward Shogulin <edward.shogulin@gmail.com>
 2026-01-15 04:25:15 +08:00
Simo Lin
f091858304 [gRPC] Add GetLoads RPC for comprehensive load metrics (#17087) 2026-01-14 12:05:10 -08:00
Aurick Qiao
5b1215d9da fix session request with None tokenizer (#16278) 2026-01-14 10:41:08 -08:00
Douglas Yang
aa2b4f7661 fix: renaming test file and job names + skip blocking llama4 nightly (#16971) 2026-01-14 09:57:59 -08:00
Simo Lin
b3a3f51320 [API] Add /v1/loads endpoint for load metrics (#16976) 2026-01-14 09:13:20 -08:00
shuwenn
de94d793ad feat: support qwen3(-VL) rerank scoring&chat template (#16403) 
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
 2026-01-15 00:45:46 +08:00
Xiaoyu Zhang
0d904ef44c [diffusion] fix: fix fsdp tp load make param miss parallel meta data (#17058) 2026-01-15 00:12:33 +08:00
Yuan Luo
969faaa410 [diffusion] fix: revise fa4 backend to support blackwell (#17077) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-01-14 23:31:46 +08:00
shuwenn
48c2aca9ba [Env] centralize pd vars in environ.py (#16264) 2026-01-14 23:06:01 +08:00
fxmarty-amd
5af84c8af5 [AMD][Quantization] Add int4fp8_moe online quantization on ROCm (#7392) 
Co-authored-by: Dehua Tang <dehtang@amd.com>
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: YC Tseng <yctseng@amd.com>
 2026-01-14 01:44:40 -08:00
Yuan Luo
feae615b11 [VLM] Support ViT CUDA Graph for InternVL (#16732) 2026-01-14 17:29:23 +08:00
Netanel Haber
e75299a111 Fix issues/16714: Revert comment out of tl.debug_barrier() in causal_conv1d_triton (#16899) 
Co-authored-by: Yi Zhang <1109276519@qq.com>
 2026-01-14 17:26:48 +08:00
roikoren755
72bacc88c8 [NemotronH] Use ReplicatedLinear for fc1_latent_proj (#16569) 
Signed-off-by: Roi Koren <roik@nvidia.com>
 2026-01-14 17:08:27 +08:00
shaharmor98
ba625c2d90 Feat/support nemotron h mtp (#17013) 
Signed-off-by: Shahar Mor <smor@nvidia.com>
 2026-01-14 16:30:35 +08:00
Michael
b025cff441 [AMD] Add AMD CI registration (1-gpu unit test) to nightly CI. (#16941) 2026-01-13 23:41:45 -08:00
HuangJi
030496eb06 [diffusion] fix: fix --warmup-resolutions' conflict with CacheDiT (#16962) 2026-01-14 14:44:10 +08:00
sglang-bot
c86ca12875 chore: bump sgl-kernel version to 0.3.21 (#16888) 
Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>
 2026-01-14 13:27:49 +08:00
shuwenn
cd33694585 feat: add --admin-api-key for finer-grained endpoint auth (#15908) 
Co-authored-by: Simo Lin <linsimo.mark@gmail.com>
 2026-01-13 20:21:55 -08:00
Alison Shao
c5e363e8e0 test: split Qwen3 Next tests and disable PCG tests due to intermittent failures (#16989) 2026-01-13 20:18:42 -08:00
Alison Shao
9479eca75d [CI] Fix max_parallel for scheduled runs (#17046) 2026-01-13 20:16:32 -08:00
Mick
a5348eac4c [diffusion] chore: avoid raising error when output resolution is not optimal (#17030) 2026-01-14 11:36:27 +08:00
Mick
9524040220 [diffusion] chore: refactor warmup logic (#17027) 2026-01-14 11:35:06 +08:00
ybyang
2122fea3c4 Update deepseekV32 Cp doc (#17054) 2026-01-14 11:19:26 +08:00
Liangsheng Yin
e2c8a50b38 fix grammar timeout sync across tp ranks. (#16898) 2026-01-14 10:26:31 +08:00
Lianmin Zheng
a4825ed588 Fix kernel type annotations for fp8 quant and logging (#16994) 2026-01-13 18:14:32 -08:00
Hubert Lu
afe285f7bd [AMD] enable CUDA graph for NSA backend and fix NSA FP8 fused RMSNorm group quant (#16841) 
Co-authored-by: wufann <715544327@qq.com>
 2026-01-13 17:36:01 -08:00
Ziwen Zhao
cf25852a1d [model-gateway] add --disable-health-check option to skip worker health probes (#17002) 2026-01-13 17:28:32 -08:00
Tony Lu
5938c3b06a [model-gateway] HA - Lightweight State Layer + gRPC Mesh (#14108) 
Signed-off-by: Kun(llfl) <i@imux.top>
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Co-authored-by: Kun(llfl) <i@imux.top>
 2026-01-13 17:03:39 -08:00
Alison Shao
b880607108 Add 5090 dry run stage to PR test workflow (#17022) 2026-01-13 14:12:33 -08:00
Byron Hsu
339915ce2b [logprob] Fix logprob + streaming for long concurrent decode by caching already processed logprob (#17005) 
Co-authored-by: root <root@memx-cge-29-sr1.xpop.twttr.net>
 2026-01-13 12:39:14 -08:00
Lianmin Zheng
075c5a5789 Code clean up for fp8 quantization (#16982) 2026-01-13 12:38:39 -08:00
Yuhao Yang
a0b4ba9032 [diffusion] model: GLM-Image (#16894) 
Co-authored-by: jianyingzhu <53300651@qq.com>
 2026-01-14 02:02:03 +08:00
Junrong Lin
2a7b67adff [CI/NPU] Fix ascend CI issue (#16953) 2026-01-13 23:39:12 +08:00
elvischenv
1d811094f8 [Misc] Auto download question file for benchmark/mtbench (#17019) 2026-01-13 10:34:29 -05:00
Xiaoyu Zhang
2ab3ed3e9e Fix sgl-kernel per_token_quant fp8 kernel scale shared_memory bug (#16886) 2026-01-13 23:22:05 +08:00
Praneth Paruchuri
250477d2ac [model-gateway] Optimize L1 cache insertion with incremental hashing and tokenization (#16259) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Simo Lin <linsimo.mark@gmail.com>
 2026-01-13 06:24:25 -08:00
Praneth Paruchuri
af1232b2f2 [model-gateway] fix wasm example (#16924) 2026-01-13 06:21:47 -08:00
Mick
7a869045b6 [diffusion] chore: clean excessive document (#16986) 2026-01-13 21:33:50 +08:00
ahb13
888d7e54d1 [diffusion] fix: fix compatibility issue with torch.compile and flash attention v4 (#16790) 
Co-authored-by: root <root@nimrodb200.tail5cbfe.ts.net>
Co-authored-by: ahb13 <ahb13@qq.com>
 2026-01-13 21:11:19 +08:00
qichu-yun
3cb1fbaee4 [diffusion] fix: fix Qwen-Image-Edit Lightning LoRA alpha/rank scaling (read per-layer *.alpha) (#16935) 2026-01-13 21:09:11 +08:00
DarkSharpness
ba9f6d8f26 [Refactor] Clean up JIT kernel utilites (#16884) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
 2026-01-13 17:54:16 +08:00
Xiaoyu Zhang
740d3c0b39 [Diffusion] Remove useless dependency in diffusion (#16967) 2026-01-13 17:25:53 +08:00
Hubert Lu
8716589826 [AMD][Diffusion] support timestep embedding kernel for AMD GPUs (#16766) 2026-01-12 22:17:07 -08:00
fzyzcjy
ff3ddb9d9b Support min num routing keys in key-based load balancing policy (#16564) 2026-01-12 21:38:03 -08:00
fzyzcjy
9d3018f484 Support min load besides random routing key assignment policy in ManualPolicy (#16767) 2026-01-12 18:31:18 -08:00
HuangJi
a83484275d [diffusion] perf: optimize linear calculation in SLA (#16648) 2026-01-13 09:38:35 +08:00
Mick
47d485f35f [diffusion] fix: fix not respecting dit_layerwise_offload server arg (#16252) 2026-01-13 09:29:07 +08:00
Mick
2b42309955 [diffusion] UX: provide solutions for OOM (#16940) 2026-01-13 09:25:27 +08:00
James
ae0baefb94 [NPU] upgrade npu mf_apater plugin (#15853) 2026-01-13 09:02:10 +08:00
fzyzcjy
1f0e3d7fd8 Support tracking worker routing key loads in gateway (#16765) 2026-01-13 08:07:17 +08:00