Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• bba2fc49a1 [Qwen3.5] Enable nvfp4 checkpoint (#18937) hlu1 2026-02-18 20:24:05 -08:00
• 443b1a88d1 Add batched zero copy to NIXL backend (#18850) hxieandZhiqiang Xie 2026-02-18 16:31:02 -08:00
• 462267982b [AMD] Fix mi35x dsv32 mtp nightly (#18978) Bingxu Chenandmichaelzhang-ai 2026-02-19 08:23:17 +08:00
• e2fccb2ee0 Fix flaky Qwen3-Next KL divergence tests by reverting mamba slot release (#18910) Alison Shao 2026-02-18 15:55:16 -08:00
• 2f592c3b18 [Doc] Add flashinfer_deepgemm to --fp8-gemm-backend (#18982) Mohammad Miadh Angkad 2026-02-19 03:45:47 +08:00
• 4f980f6f23 [Feature] Implement update_weights_from_disk for SGLang-D (Diffusion … (#18306) Mengyang Liuandzhaochenyang20 2026-02-18 11:24:07 -08:00
• 150ed881be [4/N] Quantization Refactor: Quark MoE schemes (#18252) 4 people 2026-02-18 19:44:30 +03:00
• 9c5aae4df5 [Fix] Add lora tied lm head support (for Qwen2.5, Gemma, etc model need) (#18634) Ethan (Yusheng) Su 2026-02-18 09:34:51 -07:00
• 5a7ae059e3 Add DP ViT support for Kimi K2.5 (#18689) Yuhao Yang 2026-02-18 23:03:07 +08:00
• eb6ff4a940 [diffusion] fix: refactor task resolution logic in benchmark function for multimodal generation (#18948) zijiexia 2026-02-18 04:57:42 -08:00
• 0215d47007 [AMD] ROCm7.2: Add /sgl-workspace/aiter to PYTHONPATH (#18972) HAI 2026-02-18 02:21:39 -08:00
• 90d5e27f79 Enable fa3 PDL by compiling it with corresponding flags (#18756) Qiaolin Yu 2026-02-18 01:12:05 -08:00
• 390c154306 [Tiny fix] Super tiny fix mul_add naive forward bug (#18964) Xiaoyu Zhang 2026-02-18 16:18:43 +08:00
• 513c12d23f Remove unused fast-hadamard-transform PyTorch extension sources (#18927) Xiaoyu Zhang 2026-02-18 15:51:07 +08:00
• 934b36693c Reasoning models fix docs (#18963) HAI 2026-02-17 23:05:55 -08:00
• 420a611275 [diffusion] refactor: unify SamplingParams construction and improve DiffGenerator return types (#18928) Mick 2026-02-18 14:56:58 +08:00
• 9d138685c1 [Refactor] Fix test and clean up hicache code (#18555) DarkSharpness 2026-02-18 14:37:46 +08:00
• 95c44cea29 [feat] Add return_routed_experts param to async_generate for parity with generate (#18508) William Arnold 2026-02-18 15:11:19 +09:00
• ac0e493329 feat: add nsa and swa disagg support with nixl (#18939) Neal Vaidya 2026-02-17 21:13:26 -08:00
• 2d85f01d43 Revert "Fix generated-shared-prefix bench_serving" (#18956) Liangsheng Yin 2026-02-17 20:43:55 -08:00
• fa5698d791 feat: [Qwen3.5] Support block-wise FP8 quantization and model adaptation (#18926) Zheng Li 2026-02-18 11:44:25 +08:00
• 83e24e2eb4 Expose priority parameter in Engine.generate() and Engine.async_generate() (#18944) Yan Ru PeiandCursor 2026-02-17 19:14:22 -08:00
• 34d975b18f Fix eval tests not capturing server launch failures (#18886) Alison Shao 2026-02-17 15:59:03 -08:00
• e02a9bec8d Refactor sampler: Use a better hash function for deterministic sampling and clear dispatch for probs/logprobs/logits sampling paths (#18915) Lianmin ZhengandSehoon Kim 2026-02-17 15:41:23 -08:00
• 83a475e8d7 feat: add cuda core dump CI warpper (#18909) Liangsheng Yin 2026-02-17 14:49:26 -08:00
• 9a7d6be567 cleanup prefill metrics logging to fix dp-attn metrics (#18778) Ratish PandLiangsheng Yin 2026-02-18 04:05:35 +05:30
• 355127c2e9 Fix benchmark_sglang_fused_moe_triton.py (#18940) satyamk7054andSatyam Kumar 2026-02-17 14:25:37 -08:00
• 3c601db031 Fix generated-shared-prefix bench_serving (#18769) Qiaolin Yu 2026-02-17 14:00:22 -08:00
• 48fcd62d1f fix(glm-image): single-GPU T5 config + SP support for 4D latents (#18… (#18739) 3 people 2026-02-17 16:04:32 -05:00
• aeca7d348c [3/N] Quantization Refactor: ModelSlim MoE schemes (#17993) Tamir Baydasovandronnie_zheng 2026-02-17 21:38:27 +03:00
• 10569d04bb [diffusion] update code owner (#18495) ronnie_zheng 2026-02-18 01:36:06 +08:00
• bf08d3f43c [gRPC] Fix scheduler startup broken by context parallel refactor (#18933) Simo LinandChang Su 2026-02-17 08:52:11 -08:00
• 504b2c58cf [diffusion] improve: improve torch.compile for MOVA (#18914) triple-muandgemini-code-assist[bot] 2026-02-18 00:47:38 +08:00
• bf52388354 [PCG] support piecewise cuda graph for kimi-linear model (#18849) Minglei Zhu 2026-02-17 07:31:12 -08:00
• bfe34c90ff Revert "[diffusion] operator: unify rotary embedding impl" (#18929) Mick 2026-02-17 22:56:04 +08:00
• 2aa0db7d9c [Diffusion] [NPU] Fix CI run (#18921) Makcum888e 2026-02-17 16:54:19 +03:00
• 8bb1037796 ROCm use rotary_embedding from sgl-kernel (#18920) HAI 2026-02-17 03:00:37 -08:00
• 5f81ec1ad5 [Diffusion] Fix get model name when model local path end with "/" (#18918) Makcum888e 2026-02-17 13:19:54 +03:00
• f6cc02489f [diffusion]: fix sparse video gen 2 backend being applied to cross-attention (#18900) Ratish Pandronnie_zheng 2026-02-17 15:47:46 +05:30
• b158f5d4a2 Revert "[AMD] Fix RotaryEmbedding crash on AMD/ROCm (regression from #17934)" (#18922) HAI 2026-02-17 01:07:50 -08:00
• 14c95d255c [Diffusion] [NPU] [Doc] Add NPU documentation for sglang-diffusion (#18894) Makcum888eandgemini-code-assist[bot] 2026-02-17 10:12:20 +03:00
• 899e2be7d0 [TBO] fix cuda graph intermittently becomes disabled bug (#18320) billishyahao 2026-02-17 14:18:57 +08:00
• 5e3103a787 [AMD] Fix RotaryEmbedding crash on AMD/ROCm (regression from #17934) (#18903) Michaelandmichaelzhang-ai 2026-02-16 20:59:40 -08:00
• 90a0d66e1e [Tiny] Fix assert syntax warning in compressed_tensors_w4a4_mxint4_moe.py (#18899) Mohammad Miadh Angkad 2026-02-17 12:54:30 +08:00
• 7e41ac6c8d Skip flaky test_tool_choice_required_non_streaming for Mistral (#18889) Alison Shao 2026-02-16 20:50:55 -08:00
• d5307ce022 [misc] adding metadata field in UpdateWeightFromDiskReqInput (#18821) Yilong Zhao 2026-02-16 20:14:15 -08:00
• 26b2c63d03 [diffusion] operator: unify rotary embedding impl (#18164) triple-muandgemini-code-assist[bot] 2026-02-17 12:02:48 +08:00
• b21390f8f3 Adapt the Qwen2Model._update_causal_mask for transformers==4.57.1 (#18774) pansicheng 2026-02-17 10:20:41 +08:00
• 50ca24aebb [diffusion]: fix scheduler crash on ZMQ messages with unexpected frame counts (#17890) Ratish PandXiaoyu Zhang 2026-02-17 07:15:05 +05:30
• f9c3def7fe Fix CI: add flashinfer --download-cubin to install dependencies (#18887) Alison ShaoandLiangsheng Yin 2026-02-16 13:50:10 -08:00
• 1b659bcb08 Fix GLM-5 fused shared expert (#18804) 4 people 2026-02-17 03:50:39 +08:00
• 0ff24159a5 Fix modelopt FP8 create weights (#18447) danielafrimi 2026-02-16 18:59:50 +02:00
• eba6af385d [2/N] Quantization Refactor: Compressed tensors MoE schemes (#17503) 4 people 2026-02-16 18:03:51 +03:00
• 1b3513a7e4 refactor FAKE transfer backend and remove --disaggregation-decode-enable-fake-auto parameter (#18345) Estrella-xx 2026-02-16 22:27:02 +08:00
• c1d1337afc [diffusion][Wan]: fix sparse attention backends being applied to cross-attention (#17596) Ratish P 2026-02-16 19:27:58 +05:30
• b86c6491fa [Perf] ~9.5x faster Blackwell MXFP4 MoE weight loading (#18858) Mohammad Miadh Angkad 2026-02-16 19:47:09 +08:00
• 4f0409f8aa [Model] Add Qwen3ForRewardModel and fix Qwen3ForSequenceClassification (#17992) Shivam jindalandyes-its-shivam 2026-02-16 17:14:41 +05:30
• de833f9e8e Revert "[diffusion]: Improve layerwise offload buffer reuse and shared-storage handling" (#18866) Mick 2026-02-16 18:00:58 +08:00
• d0c94e136a [diffusion] logging: improve peak vram logging (#18865) Mick 2026-02-16 16:44:37 +08:00
• ed22720c07 [JIT kernel] hd=512,1024 in JIT QK norm (cta based) (#17515) Yi Zhong 2026-02-16 03:07:24 -05:00
• 206accd15d Fix GLM-4V processor registration when glm_ocr is unavailable (#18885) Alison Shao 2026-02-16 00:02:31 -08:00
• 61da34ad0b [diffusion] fix: fix LoRA weight snapshot aliasing in unmerge logic (#18883) Changyi Yang 2026-02-16 02:39:45 -05:00
• d85884ca57 Update ascend_npu_qwen3_5_examples.md (#18888) RAY 2026-02-16 15:24:27 +08:00
• 86c181e335 Fix test_lora_qwen3 nightly failure: replace adapter with added_tokens (#18884) Alison Shao 2026-02-15 22:35:06 -08:00
• f1efb46bdd fix: adding performance logging for nightly diffusion (#18023) Douglas Yang 2026-02-15 22:09:00 -08:00
• 2050875424 fix: unifying docker image build pipeline (#18814) Douglas Yang 2026-02-15 22:05:55 -08:00
• f554b3c27b Support dumping gradients, parameters, lazy values (#18881) fzyzcjyandYueming Yuan 2026-02-16 13:34:06 +08:00
• 9a7d8d5eb0 Collect upper level metadata to dump output (#18880) fzyzcjy 2026-02-16 13:31:19 +08:00
• 949792d0c6 Change dump output format to dict with value and metadata (#18879) fzyzcjy 2026-02-16 13:30:47 +08:00
• 02816abc0d Flip dumper to disable by default and refactor environment handling (#18878) fzyzcjy 2026-02-16 13:29:32 +08:00
• 5ddc84e33e [AMD] MORI-EP inter kernel type switch (#18437) Duyi-WangandHAI 2026-02-16 12:59:39 +08:00
• bc79a64d3a [Diff]: support SGLANG_TORCH_PROFILER_DIR environment variable for profiler log directory (#18454) Johnsonmsandgemini-code-assist[bot] 2026-02-15 20:47:29 -08:00
• 0af9dcc407 [diffusion] refactor: refactor server_args adjust and validate logics (#18863) Mick 2026-02-16 11:49:06 +08:00
• 78b4c9e248 [diffusion] fix: avoid saving output for warmup requests (#18867) Mick 2026-02-16 11:48:28 +08:00
• 8a82c70297 [VLM] Optimize Ernie4.5-VL rotary embedding with fused triton kernel (#18856) Yuan Luoandluoyuan.luo 2026-02-16 11:19:44 +08:00
• 45715af50c fix: nightly whl dev date suffix (#18873) Douglas Yang 2026-02-15 18:57:37 -08:00
• 0ffd0a3995 Nsa trtllm mla sparse fp8 support with Deepseek v3.2 NVFP4 (#18389) Rain Jiang 2026-02-15 17:29:54 -08:00
• 8290171f52 [CI] Remove --mem-fraction-static 0.93 from gpt-oss test (#18869) Mohammad Miadh Angkad 2026-02-16 09:24:11 +08:00
• d3bae71e3f Add claude skills for sgl-kernel and jit-kernel (#18855) Xiaoyu Zhang 2026-02-16 07:14:03 +08:00
• fd5a45d5cf Update ascend_npu_support.rst (#18868) chenxu214 2026-02-16 01:41:38 +08:00
• f2d72866e9 Create ascend_npu_qwen3_5_examples.md (#18864) chenxu214 2026-02-16 01:15:20 +08:00
• 0d30896015 fix(sgl-kernel): use >= 120 for SM12x CUDA kernel dispatch (#18750) blake-sncandClaude Opus 4.6 2026-02-15 08:44:47 -08:00
• 5fc328465a fix(sgl-kernel): support CUDA 13 runtime preloading for DGX Spark (#18747) blake-sncandClaude Opus 4.6 2026-02-15 08:43:04 -08:00
• b79808bee2 Fix libnuma.so does not exsit (#15355) 4 people 2026-02-16 00:37:50 +08:00
• 48eac1b62d Improve profiler options for bench_serving (#16991) akhilg-nv 2026-02-15 08:36:01 -08:00
• f759960ac2 feat: expose consistent_hashing policy in Python router CLI args (#17972) Blake Ledden 2026-02-15 08:33:24 -08:00
• 597d17dd18 Use ephemeral nccl port via get_free_port() (#18009) Chanh NguyenandChanh Nguyen 2026-02-15 08:32:47 -08:00
• 7a607c4900 fix_get_quant_method_in_fused_moe_condition (#18459) tjp_zjuandPeng Zhang 2026-02-16 00:31:42 +08:00
• 536ed3143b test: add test for Modelopt FP8 on SM90 (#18463) 3 people 2026-02-15 08:29:37 -08:00
• b2f74d660a fix: add SM110 (Jetson AGX Thor) to Blackwell capability check (#18787) WiwilZ 2026-02-16 00:26:58 +08:00
• 57f7e06cb9 fix: update Blackwell log/error messages to include SM12x (#18751) blake-sncandClaude Opus 4.6 2026-02-15 08:23:51 -08:00
• 07a24f1a38 update pre-commit config (#18860) SoluMilken 2026-02-16 00:18:31 +08:00
• f7603203b0 Enable DeepGemm fast warmup in CI to prevent cold-cache timeouts (#18823) Alison Shao 2026-02-15 08:02:30 -08:00
• 4ef8ece08a feature: adding build commit to sgl kernel workflow (#18853) Douglas Yang 2026-02-15 07:28:43 -08:00
• ddfe147377 [diffusion]: Improve layerwise offload buffer reuse and shared-storage handling (#18611) Ratish P 2026-02-15 19:47:51 +05:30
• 4e162d4b1b change npu.dockerfile (#18835) chenxu214 2026-02-15 20:43:15 +08:00
• 3feb48139e [diffusion] quant: add support for svdquant and nunchaku (#18549) 3 people 2026-02-15 20:43:00 +08:00
• 88010e9601 [AMD] Fix nightly 1-GPU test failures and bench_serving regression (#18761) Michaelandmichaelzhang-ai 2026-02-15 04:36:47 -08:00
• 90555a0228 Add missing dumper tests (#18859) fzyzcjy 2026-02-15 18:42:57 +08:00
• 4c7f986c6b Extract dumper and prefill delayer tests common utils (#18857) fzyzcjy 2026-02-15 18:33:23 +08:00