chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity
9,079 Commits 1 Branch 0 Tags
bcc6d84f93fbfbbb64bf4c86356147acee042750
Commit Graph

1673 Commits

Author SHA1 Message Date
strgrb
bcc6d84f93 Use fused_sigmoid_gating_delta_rule_update_kernel for KDA (#17108) 2026-01-21 19:24:29 +08:00
Sam Shleifer
0d49b13fdd Fix circular import in quantization modules (#17372) 2026-01-21 15:47:09 +08:00
Baizhou Zhang
8251a74d5f [Tiny] Backward compatibility for fp4 gemm flags (#17466) 2026-01-21 14:34:40 +08:00
Ke Bao
d97066d209 Use attn_tp_group for all reduce in token embedding (#17403) 2026-01-20 23:56:21 +08:00
BingjiaWang
612026ad2c [OPT] DeepSeekV3.2: optimize indexer weight_proj-mma performance (#17205) 2026-01-20 23:09:44 +08:00
Yuan Luo
e6b7c04947 [Kimi-Linear] Refactor kimi-linear gate calculation to avoid duplicated code (#17160) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-01-20 14:29:24 +08:00
Thomas Wang
6988a0f570 Disable mla persistent kernel when not using fp8 kv_cache (#17327) 2026-01-19 20:29:54 -08:00
shuwenn
8fb45523f3 feat: support bitsandbytes quantization algorithm (#15325) 2026-01-19 18:36:56 -08:00
b8zhong
f374623fa9 [Refactor] Set fp4-gemm-backend=auto on SM100 and rename fp4-gemm-backend with flashinfer_ prefix (#17309) 2026-01-19 20:09:07 +08:00
Shu Wang
5c02217746 Inclusion of nvfp4 blockscale in EPLB Rebalance (#17158) 2026-01-19 17:45:27 +08:00
yudian0504
9fe56cd0fb Fix kernel selection in biased_grouped_topk_gpu (#17325) 2026-01-19 14:06:11 +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
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
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
Nan Jiang
dd99f818e0 fix: fix regression and unclear pattern (#16561) 2026-01-16 23:21:42 -08:00
b8zhong
d36f6f043c [Fix] flashinfer_trtllm intermediate_size assertion with Qwen3 + TP=8 (#16824) 2026-01-17 09:24:05 +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
b8zhong
4346db5faf [Fix] Remove assertion for padding for NVFP4 weight scales to fix GLM 4.5 NVFP4 (#12497) 2026-01-15 08:57:14 +08:00
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
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
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
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
Lianmin Zheng
075c5a5789 Code clean up for fp8 quantization (#16982) 2026-01-13 12:38:39 -08:00
Yinghai Lu
d3c08fb07c [layers] support zero-dim rmsnorm (#16978) 2026-01-12 15:53:19 -08:00
Gaoji Liu
7b682de870 [Model] Support IQuest-Coder-40B-Loop (#16348) 
Co-authored-by: yxing <yxing@iquestlab.com>
Co-authored-by: yzhu <yzhu@ubiquant.com>
Co-authored-by: zelong518 <zelonghuang02@gmail.com>
 2026-01-12 23:44:45 +08:00
Xun Sun
9f5cd80a8d Re-introduce the unit test of test_mooncake_ep_small (#16019) 2026-01-12 17:01:24 +08:00
Yibo Cai
2f4a6addf3 [cpu/arm64] support run sglang on arm64 cpu (#14867) 2026-01-11 04:27:19 -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
Qiaolin Yu
206db66f5c tiny refactor pcg split op registration (#16863) 2026-01-10 23:45:28 +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
YAMY
3fd88ea9b5 [MTP][spec_v2] Fix TRTLLM MLA backend crash in EAGLE draft_extend mode (#15790) 2026-01-10 19:58:23 +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
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
Liangsheng Yin
e6d40bff81 Revert "feat: reduce constrained-decoding overhead in TP" (#16845) 2026-01-10 11:39:38 +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
Hubert Lu
d6d5c3fdea [AMD] Clean up vllm dependencies in moe_runner/triton.py (#11349) 
Co-authored-by: HAI <hixiao@gmail.com>
 2026-01-09 00:24:04 -08:00
Alison Shao
e46f79431b Fix external_models import path and migrate model loading tests (#16458) 2026-01-08 23:43:49 -08:00
Hanming Lu
41609b52fe support page size large than 64 for mamba radix cache with fix (#16768) 2026-01-09 13:28:37 +08:00
Yongfei Xu
05dfef92a1 [DeepSeek 3.2] Support and optimize pipeline parallelis when context pipeline enabled (#16380) 
Co-authored-by: ybyang <ybyang7@iflytek.com>
 2026-01-09 11:01:49 +08:00
Mohammad Miadh Angkad
05ab110e02 [Performance] Force split_k=1 for MXFP4 Triton kernels on Hopper (#16014) 
Signed-off-by: Mohammad Miadh Angkad <MAngkad.BSDSBA2027@aim.edu>
 2026-01-08 23:52:22 +08:00
luoyuyan
fb7609f1dd Fix FP8 MoE NaN with DeepGEMM on Blackwell (#16622) 2026-01-08 22:24:12 +08:00
chenxu214
7dd679cbb9 [NPU][Bugfix] Fix qwen3 error when enable-dp-lm-head (#16115) 2026-01-08 15:15:43 +08:00
陈一涵
48b8dcd42e [jit kernel] support dtype as a cpp template parameter (#16452) 2026-01-08 13:54:33 +08:00