Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• 39e83d1401 [CI] Eliminate per-arch Docker tags by using push-by-digest (#20793) Lianmin ZhengandClaude Opus 4.6 2026-03-18 12:35:06 -07:00
• b9dba851a0 Fix streaming token ids data loss under load (#19977) Vladislav Nosivskoyandishandhanani 2026-03-18 22:23:45 +03:00
• 70876ae93b fix: guard configure_deep_gemm_num_sms when JIT disabled (#20868) Gabriel WuandClaude Opus 4.6 2026-03-19 02:15:20 +08:00
• a6c7bb54eb [Perf]Optimize waiting queue update with set usage (#20503) Jackie 2026-03-19 00:56:24 +08:00
• 20a23e3173 [SKILL] Refine kernel authoring docs and validate add-jit-kernel / add-sgl-kernel end to end with Codex (#20867) Xiaoyu Zhang 2026-03-18 23:00:33 +08:00
• 21c4fc6334 [DP encoder] Fix pos_emb layer TP issue when DP encoder enabled for Qwen3 VL (#20788) jianan-gu 2026-03-18 17:14:47 +08:00
• 05c00088e3 Cleanup broken dist-info directories in ci deps install (#20817) Ke Bao 2026-03-18 17:09:23 +08:00
• c0a4408f78 [AMD] Fix dpsk-v32 accuracy issue on mi355 (#20840) Thomas Wang 2026-03-18 17:06:15 +08:00
• f0d7a3f427 [AMD][TBO] Fix mori ep dual stream accuracy (#19888) billishyahao 2026-03-18 17:00:55 +08:00
• 8b46f1f4ec [PD] Add retry interval in ensure_prefill_info (#20832) Shangming Cai 2026-03-18 16:02:20 +08:00
• 93422f27d6 [AMD][AITER] Guard _use_mla_ps_kernel with self.use_mla in draft_extend_v2 paths (#20409) Chuan (Richard) Li 2026-03-18 00:45:22 -07:00
• ead9d7aa43 [diffusion] fix: fix vae model offload on mps(#20607) R0CKSTARandgemini-code-assist[bot] 2026-03-18 15:44:59 +08:00
• 532470bcca [NPU] add new fusion operator DispatchFFNCombine (#20245) chenxu214 2026-03-18 15:22:04 +08:00
• ae15fca192 [Bugfix] fix hicache mooncake backend extra config loading (#16808) 3 people 2026-03-18 15:07:39 +08:00
• d20e9a20fa [JIT] Inject target architecture flag into JIT compilation (#20103) xingsy97 2026-03-18 14:16:49 +08:00
• f78d5c3b3c [JIT Kernel] Add hadamard kernel test and benchmark (#20030) xingsy97 2026-03-18 14:16:35 +08:00
• c64681f162 [Bugfix] [diffusion] Fix cache-dit with sp-degree only (#19965) 3 people 2026-03-18 09:05:12 +03:00
• b6055e59cd [HiCache] Reduce per-request backup log noise (#20813) Kangyan-ZhouandClaude Opus 4.6 2026-03-17 22:47:14 -07:00
• 30a35ecd90 Add gigachat3.1 parser (#19886) ViacheslavandViacheslav Barinov 2026-03-18 08:45:01 +03:00
• 2e860233ca rocm: fix oom when loading fp8 weights close to size of available vram (#19941) Evgueni Petrov 2026-03-18 12:44:19 +07:00
• 0acc1d3c9a fix: change qwen 3.5 linear attention a_log to fp32 (#19961) shiyu7andsunqi.7 2026-03-18 13:42:06 +08:00
• 88c40ec16d Use Flashinfer for target_verify in GDN model for SM120 (#20604) Brayden Zhong 2026-03-18 01:40:56 -04:00
• 97d5386a21 Use TRTLLM allreduce fusion for Qwen 3.5 (#19889) Brayden Zhong 2026-03-18 01:40:22 -04:00
• 1b690836fa Add ut coverage workflow (#20804) Ke Bao 2026-03-18 13:25:53 +08:00
• c42da50289 Update test guide to contribution guide (#20805) Ke Bao 2026-03-18 13:25:16 +08:00
• 9c87e137ee [GDN] Support GDN packed decode (#20627) Yuan Luo 2026-03-18 13:20:07 +08:00
• 4cc19862ef [NVIDIA] Integrate FlashInfer decode kernel (Blackwell) for Qwen3.5 (#19150) Kaixi HouandClaude Sonnet 4.6 2026-03-17 22:11:18 -07:00
• da24478913 [AMD] Fix CI: update transformers in Qwen 3.5 and GLM-5 nightly tests (#20750) Michael 2026-03-17 22:07:07 -07:00
• c43d495dd5 [RadixTree][9/N Refactor]: Support unified init_load_back params (#20590) hzh0425 2026-03-18 11:19:52 +08:00
• f15b3338c9 Revert "[Bugfix] Fix GLM-4.6V vision regression in glm4v_moe and glm_ocr" (#20740) Mick 2026-03-18 10:09:50 +08:00
• 944355c66f [Bugfix] Fix model output corruption caused by EPLB rebalance (Eager and CUDA Graph modes) (#18213) lviyandFortPercent 2026-03-18 09:30:24 +08:00
• 41c8651c0d Revert "[AMD] CI - skip tests on mi325 (#20660)" (#20802) YC Yen-Ching Tseng 2026-03-18 09:01:51 +08:00
• 4d3976b6c5 [HiCache] Check in-flight async ops in is_fully_idle() before attach/detach (#20746) Liangsheng Yin 2026-03-17 17:28:26 -07:00
• c5d2528bff Revert "[AMD][MORI] Fix MTP crash with FP4/FP8 dispatch and add NEXTN dispatch env vars." (#20797) Qiaolin Yu 2026-03-17 17:28:09 -07:00
• 2acb20f53b [Disagg] Non-blocking try_ensure_parallel_info in pending queue, consolidate rank mapping into PrefillServerInfo (#20785) Shangming Caiandhnyls2002 2026-03-18 08:26:18 +08:00
• cb1e63aba4 bump fa4 to official released fa4 pkg (#20303) Rain Jiang 2026-03-17 17:22:56 -07:00
• c77d7c629e [Bugfix] Fix MTP prefill cuda graph logging (#20279) Jincong Chenandgemini-code-assist[bot] 2026-03-18 07:36:52 +08:00
• 744b1c9e6f Added fallback to individual copy_ (#20683) Kaixi 2026-03-17 22:44:38 +01:00
• a515cc38a7 Delete .editorconfig (#20795) Lianmin Zheng 2026-03-17 13:02:04 -07:00
• dc1ab5d2b2 Delete CODE_OF_CONDUCT.md (#20794) Lianmin Zheng 2026-03-17 13:01:51 -07:00
• 3d8fc9a0ca Revert "[Nvidia] Add trtllm mnnvl allreduce with unified flashinfer allreduce fusion api" (#20792) Kangyan-Zhou 2026-03-17 11:59:02 -07:00
• 666b5e4852 [NPU] Update torch and torch_npu version for NPU (#20013) Makcum888e 2026-03-17 21:25:02 +03:00
• 09f5097fe4 [NPU] [Bugfix] [diffusion] Fix NZ performance bug for diffusion models (#20684) Артем Савкинandgemini-code-assist[bot] 2026-03-17 21:23:09 +03:00
• d35fea1b2b [Nvidia] Add trtllm mnnvl allreduce with unified flashinfer allreduce fusion api (#12787) Shu Wang 2026-03-17 10:02:45 -07:00
• 17031120b8 [DeepSeek v3.2][Bugfix] get_index_k_scale_buffer support cp (#18280) Yongfei Xu 2026-03-18 00:54:54 +08:00
• 466ff20e51 [Model] Fix NemotronH OOM on unified-mem systems: stream weights + safetensors cleanup (#20580) Serge Panev 2026-03-17 09:47:58 -07:00
• 24a27d5320 vlm: support piecewise cuda graph for Kimi-K2.5 (#20747) Yuhao Yang 2026-03-18 00:32:07 +08:00
• 7f99319c56 Add evict policy ut (#20787) Ke Bao 2026-03-17 22:06:14 +08:00
• b5f3eaecbc [NPU] Support dequant_swiglu_quant & moe_init_routing_v2 & npu_moe_token_unpermute for W8A8 MoE decode (#19913) heziiop 2026-03-17 21:39:29 +08:00
• 5717834f1f [diffusion] refactor: cleanup parallel_state.py (#20760) Mickandgemini-code-assist[bot] 2026-03-17 21:21:42 +08:00
• 17c81a3e07 Revert "[PD] Make pending reqs resolving more robust" (#20779) Shangming Cai 2026-03-17 20:31:12 +08:00
• cfead25bbf [Qwen3.5] mamba slice fix (Prefill TP != Decode TP & decode TP size>1) (#20655) YAMYandShangming Cai 2026-03-17 04:30:58 -07:00
• 966ae87d02 [AMD] avoid correction_bias_dtype dtype convert (#20692) AMD-yanfeiwang 2026-03-17 17:55:05 +08:00
• 5270a06488 [Disagg] Fix health check false-positive in disagg is_fully_idle (#20756) Liangsheng Yin 2026-03-17 02:18:54 -07:00
• 385a35bd11 [AMD][MORI] Fix MTP crash with FP4/FP8 dispatch and add NEXTN dispatch env vars. (#20647) Duyi-Wang 2026-03-17 16:13:42 +08:00
• ee106757df [diffusion] fix: fix Diffusers backend ignores model-specific sampling parameter (#20080) Junhao LiuandMick 2026-03-17 01:10:46 -07:00
• 9a697ceabb [Fix #20389] Illegal memory access in triton attention for large token counts (#20390) akhilg-nv 2026-03-17 00:42:11 -07:00
• e3277b3be2 [diffusion]: remove stale offload-manager in LTX2 AV denoising (#20624) Ratish P 2026-03-17 12:44:00 +05:30
• 18dd5c972d [AMD] Fix AMD CI : stage-c-large-8-gpu-amd-mi35x (#20521) YC Yen-Ching Tsengandbillisyahao 2026-03-17 14:53:33 +08:00
• 025691cd9e [diffusion] chore: bump up cache-dit & support quant for diffusers backend (#20361) DefTruth 2026-03-17 12:51:31 +08:00
• 079a1fd35e [Bugfix] Fix write-through events not processed when scheduler is idle (#20560) Rocky Song 2026-03-17 13:49:59 +09:00
• 5d5c31c6e4 [PP] Add CP pyobj broadcasting when enable dynamic CPP (#20738) Shangming Cai 2026-03-17 12:20:11 +08:00
• 855ec7017d Add check to provide hicache-storage-backend when enabling kv caching on Decode Side in PD Disaggregation (#20732) MMuzzammil1 2026-03-17 12:25:14 +09:00
• 943f34f642 Add NCCL/RCCL pre-warming to reduce P99 TTFT cold-start latency (#20477) Hubert LuandClaude Opus 4.6 2026-03-16 20:23:14 -07:00
• 5ec49a5309 Revert "[diffusion] CI: use dedicated HF token for accessing restricted models" (#20737) Mick 2026-03-17 11:22:20 +08:00
• 210d0fbaef Update ascend docs (#20674) amote-i 2026-03-17 11:14:26 +08:00
• e4d06b3db2 Fix /generate JSON serialization for non-finite top_logprobs (#20714) Jay Shaik 2026-03-17 08:37:12 +05:30
• 515b3a323d feat: support human-readable suffixes (25.6k, 1M, 1Mi) for token CLI (#20577) shuwenn 2026-03-17 11:05:33 +08:00
• 3cafb02e5b AMD/ROCm: update daily image repo to lmsysorg/sglang-rocm (#20720) HAI 2026-03-16 20:04:52 -07:00
• 9f56b471aa [Network] Use NetworkAddress for dist_init_method and loopback fallbacks (#20657) psaabandhnyls2002 2026-03-16 19:59:49 -07:00
• 71a54c1c42 update CODEOWNERS (#20733) Qiaolin Yu 2026-03-16 19:41:26 -07:00
• 4dbec2dd2b [typo] Fix typos in comments and log messages in common.py (#20723) Jason Yao 2026-03-17 10:26:59 +08:00
• 7d87a6a071 Fix spec v1 token_ids_logprobs (#20718) Qiaolin Yu 2026-03-16 19:23:28 -07:00
• 474a851ae3 [diffusion] fix: fix sampling params incorrectly override in cli (#20689) Mick 2026-03-17 08:48:10 +08:00
• 1eea744855 [diffusion] CI: enable UT (#20690) Mick 2026-03-17 07:44:04 +08:00
• 2ccdb7373e [diffusion] CI: fix consistency test workflow (#20704) Yuhao Yang 2026-03-17 07:42:30 +08:00
• 826eb21bca Fix sglang-kernel dependency on CI runners (#20715) Baizhou Zhang 2026-03-16 15:23:01 -07:00
• 5ef5806160 [Nemotron] Small reasoning parser fix (#20284) roikoren755 2026-03-16 22:29:40 +02:00
• 70a6fb53af Enable embedding lookup/lora_a logic for chunked backend (#17692) 4 people 2026-03-16 11:37:58 -07:00
• 061ec582bf fix: adding teacache.params back to sampling params as intended (#20665) Douglas Yang 2026-03-16 11:27:06 -07:00
• a4528a5737 [CI] Bring back CI test for Mamba PD Disaggregation (#20675) Shangming Cai 2026-03-17 01:04:21 +08:00
• 289cbcf482 fix: support PP2+CP8+TP8 (PP with context parallelism) (#19548) ybyang 2026-03-17 00:51:47 +08:00
• 6489f77733 [Diffusion] Fix compile graph broken by flashinfer rope (#20699) Xiaoyu Zhang 2026-03-16 23:14:27 +08:00
• d3c0f4376a Fix AssertionError crash in disagg prefill inflight queue with PP (#20686) Du Bin 2026-03-16 22:38:59 +08:00
• 15097c5c3b Release sglang kernel 0.4.0 (#20440) Xiaoyu ZhangandBaizhou Zhang 2026-03-16 20:34:58 +08:00
• 3d58cd16d9 [DP Attention] Optimize dp_padding_mode selection for dp_size=1 in extend mode (#20406) sky 2026-03-16 18:44:42 +08:00
• 549fbcc864 [5/N] (Elastic EP) Use GPU P2P to exchange expert weights during EPLB as much as possible (#12068) 3 people 2026-03-16 18:40:58 +08:00
• 3055b6906d [Diffusion] Document torch.compile graph-break checks in diffusion benchmark skills (#20681) Xiaoyu Zhang 2026-03-16 17:41:40 +08:00
• 485597e651 [diffusion] fix: fix some sampling args passed via cli are omitted (#20630) Mick 2026-03-16 16:55:30 +08:00
• 895e56097c Add NPU basic function testcases (#19382) 3 people 2026-03-16 15:09:56 +08:00
• e96a3752a0 Update timeout for some ci tests (#20664) Baizhou Zhang 2026-03-15 23:58:30 -07:00
• 42f18fe560 [HiCache] fix: release write-through lock_ref during decode (#20049) shuwenn 2026-03-16 14:49:31 +08:00
• 39336f5812 Precompute swa cache location (#20449) Ke Bao 2026-03-16 14:38:08 +08:00
• 135af6dc92 [EPD][VLM] support video/audio input (#17824) Zheng Wengangandsiyu 2026-03-16 14:18:21 +08:00
• 738cbde902 [PD] Make pending reqs resolving more robust (#20505) Shangming Cai 2026-03-16 14:12:13 +08:00
• a92872cbc3 [AMD] CI - skip tests on mi325 (#20660) YC Yen-Ching Tsengandbingxche 2026-03-16 13:35:04 +08:00
• 223a4e485b [test] Fix bfloat16 tolerance in test_selective_state_update (#20345) Roopak Srivastava 2026-03-16 09:32:01 +05:30
• 97b2a89334 [RadixTree][8/N Refactor]: unify lock interface (#20330) pansicheng 2026-03-16 11:49:51 +08:00
• f0458e0b49 [Utils] Move network/socket utilities from common.py to network.py (#20646) Liangsheng Yin 2026-03-15 20:35:24 -07:00
• afc71bae3a feat: Add 'none' reasoning effort to ChatCompletionRequest (#20556) Javier Torres 2026-03-15 20:25:48 -07:00