chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity
9,952 Commits 1 Branch 0 Tags
15f2e36fb9c548cda01eba89c4fd780589b068e8
Commit Graph

6487 Commits

Author SHA1 Message Date
silencejade
15f2e36fb9 [NPU] forward_npu uses native impl by default in MultiPlatformOp (#18545) 2026-02-25 09:16:09 +08:00
Chen, Zhentao
b9cf1563de [ROCm] Optimize Deepseek R1 on MI300X (#18242) 
Co-authored-by: Chen, Todd <zhenchen@amd.com>
 2026-02-24 17:01:14 -08:00
Vladimir221
f1088beb6a [NPU]Optimization of forward_npu for UnquantizedFusedMoEMethod (#13158) 2026-02-25 08:55:20 +08:00
Jonah Bernard
d7a03c7ebf [MoE Refactor] Refactor FlashInferFusedMoE into FusedMoE and flashinfer_trtllm.py (#19266) 2026-02-24 16:47:53 -08:00
Chen, Zhentao
c193a52fa2 [AMD] DSR1/V3 use fp8 bmm in MLA for MI300X (#18624) 
Co-authored-by: Chen, Todd <zhenchen@amd.com>
 2026-02-24 15:33:33 -08:00
Ratish P
ae6f6e1495 [Refactor] Benchmark: Add typed DatasetArgs/Loader registry and CPU dataset unit tests (#19147) 
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
 2026-02-24 12:22:01 -08:00
Glen Liu
a06425184f [Fix] remove redundant +1 when getting tail_str for Req (#18584) 2026-02-24 10:35:26 -08:00
Makcum888e
9bce3b040c [diffusion] [NPU] Update perf baselines (#19227) 2026-02-24 21:15:16 +03:00
Zihao Wang
e6ad58e5da [diffusion] fix: webui not return data (#19244) 2026-02-24 23:39:06 +08:00
Adarsh Shirawalmath
1efc33c640 [diffusion] refactor: remove enums and unify attention backends (#19149) 2026-02-24 21:21:23 +08:00
triple-mu
ea1bc1c578 [diffusion] feat: optimize all_to_all (#19157) 2026-02-24 21:20:10 +08:00
Yuan Luo
31c7dc9d99 [VLM] Introduce FlashInfer CUDNN Prefill as ViT Backend (#19003) 
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
 2026-02-24 19:49:22 +08:00
xdtbynd
1a83b2c15d fix: fix the bug blocking completion template application (#17010) 
Co-authored-by: xdtbynd <supercluster@vip.qq.com>
Co-authored-by: cy <chenyang08056032@163.com>
Co-authored-by: sglang-npu-bot <sglangnpu@163.com>
 2026-02-24 18:50:08 +08:00
Cheng Wan
6e54361608 Refactor CUDA graph input buffers with shared buffer pool (#19180) 2026-02-24 02:24:40 -08:00
jianzhao-xu
94946764a4 bugfix: The default value of the environment virable is None, so that… (#18309) 
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: sglang-npu-bot <sglangnpu@163.com>
 2026-02-24 18:10:21 +08:00
GMI Xiao Jin
fcfd964d7d [diffusion] model: LTX-2 Support PR3 (#19151) 2026-02-24 16:55:28 +08:00
Simo Lin
88a7e48108 fix(grpc): handle embedding requests in _handle_batch_output (#19221) 
Signed-off-by: Simo Lin <linsimo.mark@gmail.com>
 2026-02-23 22:32:16 -08:00
Mick
2e053d6eb6 [diffusion] quant: support quant for all dits (#19156) 
Co-authored-by: zyzshishui <zyzshishui@gmail.com>
 2026-02-24 14:20:54 +08:00
fy
4f25a48d7a support xverse_moe on npu 
Co-authored-by: sglang-npu-bot <sglangnpu@163.com>
 2026-02-24 14:11:20 +08:00
Liangsheng Yin
5e80027ac7 [PD-Disagg] Support FAKE transfer backend for more cases (#19215) 2026-02-23 20:50:43 -08:00
jianzhao-xu
d8ef33a551 bugfix: prioritize init_npu_backend to fix various initialization bugs (#17652) 2026-02-24 12:25:20 +08:00
Liangsheng Yin
feb041f4e5 [PD-Disagg] Improve type hints across all conn.py (#19208) 2026-02-23 19:44:23 -08:00
Liangsheng Yin
ea7ef63e6d [PD-Disagg] Deduplicate common KVManager methods into CommonKVManager (#19205) 
Co-authored-by: Shangming Cai <csmthu@gmail.com>
 2026-02-23 18:34:21 -08:00
Kangyan-Zhou
8aeb16f3fc fix: add missing blank line after docstring in serving_transcription.py (#19206) 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-23 18:29:38 -08:00
Xinyuan Tong
581bf53e03 Whisper model support & /v1/audio/transcriptions endpoint & benchmark (#16983) 
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: MahmoudAshraf97 <hassouna97.ma@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-02-23 17:28:37 -08:00
Liangsheng Yin
d160c5b9bb [PD-Disagg] Unify prefill info data transition flow, all with PrefillServerInfo (#19195) 2026-02-23 16:15:20 -08:00
Liangsheng Yin
9fac90d85d [CI] Tiny enhance the dp attention load blance benchmark (#19194) 2026-02-23 14:33:32 -08:00
Liangsheng Yin
2aa3fe394e [CI] fix the teardown output of disaggregation test (#19193) 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2026-02-23 12:41:03 -08:00
Liangsheng Yin
2274bfebb1 [PD-Disagg] Support query dp rank from bootstrap server. (#19168) 
Signed-off-by: Chang Huaixin (OpenAnolis) <changhuaixin@linux.alibaba.com>
Co-authored-by: Chang Huaixin (OpenAnolis) <changhuaixin@linux.alibaba.com>
 2026-02-23 10:59:30 -08:00
Linyu Wu
2cdde5d4ab [Kernel Slimming] Migrate AWQ marlin repack kernel to JIT (#18949) 
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
 2026-02-23 22:05:27 +08:00
Xiaoyu Zhang
e0e0cad6bc [Diffusion] Match rotary_embedding module name style (#19179) 2026-02-23 21:02:34 +08:00
Xiaoyu Zhang
2717393681 [Refactor] Split rotary_embedding.py into a modular package (#19144) 2026-02-23 20:05:29 +08:00
Junrong Lin
6448de7e96 Reorganize topk logic to clean up code and expose logical experts (#16945) 2026-02-23 00:30:57 -08:00
Yuzhen Zhou
4f3dc1ef5b [ROCm] Use unreg path for custom all-reduce during CUDA graph capture (#19162) 2026-02-22 23:27:31 -08:00
Changyi Yang
c3c1532820 [diffusion] feat: detect Flux2 custom VAE path from component_paths (#19170) 2026-02-23 15:19:53 +08:00
Qiaolin Yu
42b1019881 Fix bench_one_batch_server by moving the print statements (#19175) 2026-02-22 22:06:25 -08:00
Baizhou Zhang
2472e47d73 Revert "Refactor graph input buffers (#18991)" (#19173) 2026-02-23 13:09:54 +08:00
Baizhou Zhang
fa80b9beba [CI] Skip some subtests for tool call parser (#19172) 2026-02-23 12:20:12 +08:00
Ratish P
0e670c36d6 fix(diffusion): enforce strict input_reference validation for T2V (#14825) 
Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>
 2026-02-23 12:04:06 +08:00
Baizhou Zhang
43f83525c0 Revert "[AMD] support two batch overlapping for mori ep #17953" (#19161) 2026-02-23 01:19:23 +08:00
Mick
45095bac70 [diffusion] refactor: rename quantized model path server arg (#19142) 2026-02-22 23:18:35 +08:00
Talor Abramovich
c6a99e43b9 Fix corrupted JSONL metrics file due to concurrent writes (#19011) 2026-02-22 20:33:27 +08:00
Mick
7d4860bc5e [diffusion] CI: relax perf check threshold (#19154) 2026-02-22 20:02:12 +08:00
Mick
87823722b3 [diffusion] chore: minor cleanups (#19123) 2026-02-22 19:07:25 +08:00
fzyzcjy
1a1c768d44 Support kwargs and megatron core tensor parsing in dumper (#19138) 2026-02-22 16:24:33 +08:00
Ziang Li
eddf193292 [DSv32] [GLM5] Improve Model Quality by Avoiding FP32 Precision Loss in weights_proj (#19041) 2026-02-22 16:20:51 +08:00
fzyzcjy
326b788ab4 Fix wrongly large dumped file and handle non intrusive hook reset in dumper (#19124) 2026-02-22 16:20:08 +08:00
fzyzcjy
c1f497e20e Enhance reset, states, http in dumper (#19095) 2026-02-22 16:17:41 +08:00
fzyzcjy
4091b720c5 Support multi colocated dumper, named exp cleanup, argparse config (#19094) 2026-02-22 16:16:15 +08:00
fzyzcjy
31f0c11405 Configure and call dumper in main SGLang logic (#19093) 2026-02-22 16:14:27 +08:00