chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Commit Graph

  • 24c91001cf [model-gateway] code clean up in tokenizer register step workflow (#16316) Chang Su 2026-01-02 16:05:10 -08:00
  • c4edcac6d7 refactor(core): remove get_by_model_fast alias in worker_registry (#16313) Chang Su 2026-01-02 16:04:23 -08:00
  • e93433892b refactor(steps): consolidate duplicate strip_protocol function (#16318) Chang Su 2026-01-02 16:02:42 -08:00
  • a2d4f58a96 fix(http): use 504 Gateway Timeout for upstream timeouts (#16320) Chang Su 2026-01-02 16:01:44 -08:00
  • f66b091699 refactor(http): improve pd_types.rs documentation and style (#16319) Chang Su 2026-01-02 16:01:11 -08:00
  • 2f623368ab refactor(core): use idiomatic .min() in calculate_delay (#16314) Chang Su 2026-01-02 15:46:13 -08:00
  • bd9a2ced47 refactor(core): use thiserror for WorkerError (#16315) Chang Su 2026-01-02 15:33:07 -08:00
  • 0ca417d9ae chore(core): remove unused serde_json import in worker.rs (#16312) Chang Su 2026-01-02 15:31:41 -08:00
  • 30cfb687fa fixed amd multimodal CI failures caused by refactor in #15812 #15813 (#16287) sunxxuns 2026-01-02 14:55:42 -08:00
  • b7c7e03d93 Fix crash dump replay script for image data replay (#16277) Chenxi Li 2026-01-02 13:42:22 -08:00
  • f0195627a9 Fix sgl-kernel jobs to skip when target_stage is specified (#16308) Alison Shao 2026-01-02 12:49:26 -08:00
  • d401d23876 [model-gateway] Add embedding correctness test comparing against HuggingFace (#16092) Simo Lin 2026-01-02 10:58:20 -08:00
  • 17041f4673 Enable /rerun-stage slash command to work on fork PRs (#16128) Alison Shao 2026-01-02 10:36:12 -08:00
  • f07e76b229 Multiple refactors of DeepSeek V32 and context parallel (#16305) Baizhou Zhang 2026-01-03 02:21:22 +08:00
  • 1cfd2b2ded [diffusion] chore: remove redundant ulysses nccl warmup (#16301) Xiaoyu Zhang 2026-01-03 00:19:35 +08:00
  • 0d244116d2 [DeepSeek v3.2] opt Context Parallelism: support fused moe, multi batch and fp8 kvcache (#13959) Yongfei Xu 2026-01-02 23:49:14 +08:00
  • 0eae831797 [diffusion] fix: Increase text length from 256 to 1024 in Qwen-Image (#16248) Changyi Yang 2026-01-02 10:25:31 -05:00
  • c483a5f45f Tiny adjust hybrid swa handling (#16292) Ke Bao 2026-01-02 23:11:23 +08:00
  • f26f6c2c99 [diffusion] fix: make lora compatible with layerwise-offload (#16298) Mick 2026-01-02 22:33:26 +08:00
  • b021332339 [NemotronH] Add latent MoE support (#16227) roikoren755 2026-01-02 16:08:58 +02:00
  • 5062537b67 [diffusion] feat: support lightweight e2e warmup for benchmarking (#16213) Mick 2026-01-02 20:10:27 +08:00
  • 698629d1f2 Add swa page table to FA3 backend forward metadata (#16267) Ke Bao 2026-01-02 20:00:43 +08:00
  • dd93e4451c Support returning customized info (#16144) Qiaolin Yu 2026-01-02 02:32:18 -05:00
  • 6c8587b5db [diffusion] fix: align negative prompt with official readme for new model (#16222) Yuhao Yang 2026-01-02 15:20:56 +08:00
  • 027042604d [distributed] Clean up MoE groups in destroy_model_parallel (#15345) Yinghai Lu 2026-01-01 22:45:14 -08:00
  • bd48ad5e6b [Diffusion] Fix broken ring_attention when use upstream fa3 (#16270) Xiaoyu Zhang 2026-01-02 14:33:12 +08:00
  • 749736ba95 Tiny fix single-gpu dumper and add tests for dumper (#16285) fzyzcjy 2026-01-02 13:30:09 +08:00
  • 7254986342 [VLM] feat: true on policy for vlm + fsdp (#14636) Nan Jiang 2026-01-01 19:54:39 -05:00
  • 00562ee14a Support cache eviction for Manual Policy (#16263) fzyzcjy 2026-01-02 08:52:01 +08:00
  • d7a8257ba5 docs: remove outdated TODO in GLM-4.7 MoE detector test (#16265) Hudson Xing 2026-01-02 02:25:23 +08:00
  • f6f7af4068 [Refactor] Clean up custom op (#15995) DarkSharpness 2026-01-01 21:41:56 +08:00
  • a3b1e8ef3d [Feature] add aligned_vector type for JIT kernel (#16162) DarkSharpness 2026-01-01 21:40:05 +08:00
  • db499e1889 Tiny add filter, support duplications, add visualizations, fix error and robustness for dump comparator (#16262) fzyzcjy 2026-01-01 17:47:00 +08:00
  • 6cf3a6dd69 Support HTTP control for dumper (#16261) fzyzcjy 2026-01-01 17:40:17 +08:00
  • 90e24f5c31 Tiny add filter, dump dict, failable save to dumper (#16260) fzyzcjy 2026-01-01 17:35:38 +08:00
  • 21de3e1406 [diffusion] webui: tiny fix loading output image (#16251) Mick 2026-01-01 14:34:49 +08:00
  • e4c1e441af Fix deprecation warning of sre_parse for python 3.13 (#16247) Lianmin Zheng 2025-12-31 21:25:09 -08:00
  • b5af283b1c ci: increase stage-b-test-small-1-gpu partitions from 4 to 5 (#16250) Alison Shao 2025-12-31 20:08:31 -08:00
  • 130c6911f8 Add a GH action for cherrypick (#16243) Kangyan-Zhou 2025-12-31 20:05:38 -08:00
  • e0e5084802 Fix parse args from file(#13911) (#14085) 1874. 2026-01-01 11:37:33 +08:00
  • 70a769bc56 Fix NPU docker release workflow (#16253) Baizhou Zhang 2026-01-01 10:53:45 +08:00
  • 3a42c5e341 [VLM] Adopt jit qk_norm kernel in VLM (#16171) Yuan Luo 2026-01-01 10:10:36 +08:00
  • 12b89e51d8 Add P90/99 e2e latency in bench_serving script (#16245) Kangyan-Zhou 2025-12-31 15:40:33 -08:00
  • 851845579c perf(tree): optimize input_char_count calculation (#16238) Simo Lin 2025-12-31 15:29:37 -08:00
  • 57d2ba9203 SGLang Tracing: Supports propagating trace headers through sgl.Engine… (#15814) Feng Su 2026-01-01 07:19:53 +08:00
  • 417e75a60f fix: use 2-gpu-runner for pp 2 NemotronH ut (#16239) Yineng Zhang 2025-12-31 12:51:33 -10:00
  • 0500fea965 fix editable install (#16241) ishandhanani 2025-12-31 14:34:54 -08:00
  • 2b461c15b4 Update logprob_start_len handling in scheduler (#16240) Cheng Wan 2025-12-31 14:11:24 -08:00
  • 5595ae142c docs: fix markdown preview (#16236) Yineng Zhang 2025-12-31 10:43:57 -10:00
  • ace6f3005f ci(benchmark): disable sccache summary annotations and fix tree output (#16233) Simo Lin 2025-12-31 11:05:21 -08:00
  • 2da49eec50 Fix XEON docker release workflow (#16107) Kangyan-Zhou 2025-12-31 09:47:01 -08:00
  • d65ae0ec7a Use a different concurrency group for release branch testing (#16202) Kangyan-Zhou 2025-12-31 09:46:43 -08:00
  • 60d7279c46 test(tree): add comprehensive unit tests and fix input_char_count bug (#16228) Simo Lin 2025-12-31 07:31:39 -08:00
  • abdf65d4f3 Fix OOM by offloading multimodal features to CPU after embedding (#16018) siyu 2025-12-31 23:02:34 +08:00
  • c1dfbc777b deprecate prefill-round-robin-balance (#16195) Huaixin Chang 2025-12-31 22:25:33 +08:00
  • 3b3c5a05c1 [CI/NPU] fix multiple NPU CI issue (#16111) Even Zhou 2025-12-31 21:14:04 +08:00
  • 2667c857a7 Fix DeepSeekV31's structural tag trigger (#13394) Muqi Li 2025-12-31 21:13:52 +08:00
  • fc643ffbc9 Download missing shards in model weights files when not in CI (#16211) Kangyan-Zhou 2025-12-31 04:42:34 -08:00
  • 4280a18a13 [diffusion] CI: add test for cache-dit (#16204) Yuhao Yang 2025-12-31 19:58:10 +08:00
  • 386e541520 Update document for Ascend NPU (#16214) Hexq0210 2025-12-31 19:03:53 +08:00
  • b6267de5ae Upgrade python version in lint ci (#16221) Ke Bao 2025-12-31 18:22:53 +08:00
  • e47afa0237 [DP]Fix sync bubble in adjust_num_token_non_padded_for_attn_tp (#16178) Baizhou Zhang 2025-12-31 17:58:18 +08:00
  • 5ed384d07b [CI/CD] re-enable lora test (#16187) Ethan (Yusheng) Su 2025-12-31 00:32:20 -08:00
  • b4ce7a6d71 [model-gateway] cache_aware eliminate String allocations in hot path (#16209) Simo Lin 2025-12-31 00:26:10 -08:00
  • 25b48564c3 [NPU][Bugfix] fix Qwen3-VL-30B-A3B-Instruct accuracy loss (#15597) cen121212 2025-12-31 15:57:38 +08:00
  • 1c360bf753 [AMD CI] add testcases to unit-test-backend-1-gpu (#16117) Bingxu Chen 2025-12-31 15:08:45 +08:00
  • 3619ec61b4 [diffusion] feat: support multi-frame image output (#15878) chhnb 2025-12-31 13:50:02 +08:00
  • db6b51a838 Add CI_PERMISSION sort hook. (#16200) Liangsheng Yin 2025-12-31 12:15:15 +08:00
  • 8a9ca41fda Move log_prefill_stats_late to correct location in PP mode (#15946) Hudson Xing 2025-12-31 12:00:24 +08:00
  • ac11e6a7c5 Add alphabetc1 into CI_PERMISSION (#16198) shuwenn 2025-12-31 11:31:47 +08:00
  • 47a660d5b9 [NemotronH] PP support (#16172) roikoren755 2025-12-31 05:16:15 +02:00
  • c0fc7a89e7 [sgl-kernel] fix: make sgl-kernel build respect MAX_JOBS (#15575) shuwenn 2025-12-31 10:44:45 +08:00
  • 5bf0d862dd [diffusion] CI: fix generate mode and add cli test (#16174) Mick 2025-12-31 09:51:48 +08:00
  • 75b72eb8b2 [cp] assert dsv3.2 cp in pd decode mode (#16156) liupeng374 2025-12-31 09:24:46 +08:00
  • bc8b526eda Fix: Handle empty func_name and None values in GLM MoE detectors (#15754) Leoyzen 2025-12-31 06:32:35 +08:00
  • 3dfff6ae3c Eagle: GPT-OSS Eagle v2 support (#14920) Izzy Putterman 2025-12-30 14:23:07 -08:00
  • ad2c1ee352 doc: mooncake store add dummy client support (#16050) EkiRui 2025-12-31 04:37:57 +08:00
  • 9940c6f592 [model-gateway]: ASCII byte comparison and probabilistic timestamp updates (#16181) Simo Lin 2025-12-30 12:28:01 -08:00
  • 00e607111a [Auto Sync] Update request_metrics_exporter.py (20251230) (#16183) Yineng Zhang 2025-12-30 09:09:41 -10:00
  • 4bc2f2e0bc [model-gateway][docs] Add Classification API documentation (#16182) Simo Lin 2025-12-30 10:53:31 -08:00
  • d17b9e6392 Fusing RMSNormTP in minimax_m2 (#14416) Roger Young 2025-12-31 02:22:07 +08:00
  • ba67e006a7 Refactor speculative algorithm registry. (#16168) Liangsheng Yin 2025-12-31 01:24:22 +08:00
  • 45f3ad2f52 [Refactor] Rename CustomOp -> MultiPlatformOp (#16175) DarkSharpness 2025-12-31 01:16:32 +08:00
  • f35b5da521 [CI] Append test variant name to markdown report header in nightly test (#16166) Baizhou Zhang 2025-12-31 00:09:24 +08:00
  • 733a0c1a37 [Diffusion] Zimage opt with qknorm and flashinfer rope (#16161) Xiaoyu Zhang 2025-12-30 23:39:32 +08:00
  • b369aaa23f [Diffusion] Refine diffusion profling doc (#16163) Xiaoyu Zhang 2025-12-30 23:38:46 +08:00
  • b973202526 Split tp model worker init (#16165) Ke Bao 2025-12-30 23:36:03 +08:00
  • cbff7ad985 dp-attention: add follow_bootstrap_room + auto load-balance; drop decode_round_robin (#16110) Mufeez Amjad 2025-12-30 09:33:06 -05:00
  • 4de59d83a1 Reduce stages of pr-test from 4 to 3. (#16173) Liangsheng Yin 2025-12-30 22:21:48 +08:00
  • 39ca57cd28 [diffusion] chore: tiny fix model config (#16159) Yuhao Yang 2025-12-30 22:11:38 +08:00
  • 3449806727 [diffusion] feat: generalize layer-wise-offload to all supported models (#16150) Mick 2025-12-30 22:06:57 +08:00
  • b3817fa93b Split model_worker init function (#16160) Ke Bao 2025-12-30 21:39:11 +08:00
  • 059428bd8a Tiny remove additional args in init_memory_pool (#16158) Ke Bao 2025-12-30 21:38:06 +08:00
  • 5d200dd8d9 [diffusion] bench: distinguish between video generation and image generation in the bench_serving (#16149) jiapingW 2025-12-30 21:29:18 +08:00
  • 7f9a3d0609 [docs][NPU]Update model and feature docs support (#16124) husf 2025-12-30 20:05:40 +08:00
  • 664f611e83 Add profiling capture support to the encoder server (#15730) Jumiar 2025-12-30 19:56:25 +08:00
  • 49adb37e37 [diffusion] chore: fix ZMQ binding and model loading for FastWan compatibility (#13978) yh0903 2025-12-30 02:09:38 -08:00
  • 7518dc3532 feat(SpecEagleV2): add standalone_worker_v2 (#12625) Gaoji Liu 2025-12-30 17:55:04 +08:00
  • b6871ba7c9 [CI] set max-parallel to 4 by default. (#16154) Liangsheng Yin 2025-12-30 17:27:48 +08:00
  • 98225be6e5 [CI] Fixing release with cut branch workflow (#16153) Baizhou Zhang 2025-12-30 17:18:02 +08:00