Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• 10c6bee74f List more CI runs for pr-test (#18650) Liangsheng Yin 2026-02-11 18:36:45 -08:00
• 41e1fd0be7 [diffusion] fix: webui cannot correctly display generated video using wan2.2 (#18473) R0CKSTARandMick 2026-02-12 10:35:39 +08:00
• c34832c02c glm5 md (#18655) liupeng374 2026-02-12 10:11:59 +08:00
• 165aff38e1 Add CI permission for Chen-0210 (#18494) Jincong Chen 2026-02-12 09:33:35 +08:00
• dc1309fc7e Avoid kimi linear stream sync (#16186) Yi Zhong 2026-02-11 20:27:22 -05:00
• 539bbf485c [Bugfix] fix config bug caused by PR #18273 (#18535) Jiayi Yan 2026-02-12 09:26:46 +08:00
• 2bd8363486 [PCG] GPT OSS Triton Kernel Support (#18405) Yuwei An 2026-02-11 17:23:55 -08:00
• f06ab17a73 [diffusion] docs: consolidate diffusion documentation into docs (#18095) 3 people 2026-02-12 08:55:07 +08:00
• 7eaf866846 [CI] Install python3-dev for Triton JIT compilation on fresh runners (#18644) Alison Shao 2026-02-11 16:28:57 -08:00
• 5875ef0a34 Clean up noisy startup log messages and refactor loader.py (#18531) Lianmin Zheng 2026-02-11 16:12:57 -08:00
• ded068a76e Add LMF2 MoE model architecture (#17997) Piotr Mazurek 2026-02-11 18:03:43 +01:00
• 5d185efb78 Fix prefill stats for dllm (#18632) Ke Bao 2026-02-12 01:00:30 +08:00
• dcc63dc545 [CI] Guard python3 call in install script for fresh runners (#18609) Alison Shao 2026-02-11 08:05:29 -08:00
• 98b5013d59 add support to enable lora with embedding models (#17780) Vedant V JhaveriandVedant Jhaveri 2026-02-11 07:19:40 -08:00
• 947927bdb5 [V3.2] Change default CP token split method to --round-robin-split (#18613) Baizhou Zhang 2026-02-11 20:14:35 +08:00
• 4f7422f7ba [NPU] support model skywork-reward-gemma2-2-27B-v0.2 (#16947) McZyWuandcy 2026-02-11 15:34:53 +08:00
• 72c1526657 Register cp-atten-allgather buffers with symm memory (#17756) sky 2026-02-11 15:26:37 +08:00
• a8eef53dc4 Fp8 prefill attn kernel integration (#18528) Thomas WangandkkHuang-amd 2026-02-11 15:23:48 +08:00
• 2cc235e795 Fix Bug on dsv3.2 (#18553) BourneSun0527 2026-02-11 14:39:01 +08:00
• d84d2063d3 [AMD] Fix Janus-Pro crash and add Kimi-K2.5 nightly test (#18269) Michael 2026-02-10 22:33:13 -08:00
• cd90346a2b Add cache hit rate UT (#18566) Liangsheng Yin 2026-02-10 21:27:41 -08:00
• 50f74285e9 Tiny fix regex warning (#18592) Liangsheng Yin 2026-02-10 21:07:53 -08:00
• 8d2892330c chore: fix some typos (#18577) cutetocuteandLiangsheng Yin 2026-02-11 12:47:41 +08:00
• a2c38f7796 Enhance SMG guide with RL rollout systems benefits (#18588) 赵晨阳 2026-02-10 20:20:45 -08:00
• 3167bcc01c [Doc] Comprehensive Guide: Navigating DP, DPA, and SMG Best Practices (#18096) 4 people 2026-02-11 10:31:28 +08:00
• 93fca0bbc3 Fix wrong prefill log. (#18570) Liangsheng Yin 2026-02-10 15:54:03 -08:00
• 2bfab1bb67 Fix radix cache key to include generated tokens in multi-turn (regression) (#16521) Yi-Chia Chenandcopilot-swe-agent[bot] 2026-02-11 06:08:34 +08:00
• 4262f5259b Tilelang sparse decode fwd for dsv32 mi355 (#18488) Thomas Wangandkk 2026-02-11 01:53:26 +08:00
• 2d38b8aca0 Revert "[sgl-kernel] upgrade deepgemm" (#18562) Baizhou Zhang 2026-02-11 01:17:40 +08:00
• 573ff55814 [NPU][docs]fix bug about hyperlink for best practice for ascend npu (#18561) husf 2026-02-11 01:03:28 +08:00
• 44603764d6 fix(config): Support setting Mamba state dtype via config file (#18532) Zheng Liand瑀澈 2026-02-11 00:20:06 +08:00
• d0d387dea1 [NPU] update npu doc (#18474) Hexq0210 2026-02-10 21:59:13 +08:00
• 99101ce30b [NPU][docs] improve docs for Best Practice on Ascend NPU (#18360) husf 2026-02-10 21:52:27 +08:00
• bec7fe9e65 [sgl-kernel] upgrade deepgemm (#18362) Xiaoyu Zhang 2026-02-10 21:31:30 +08:00
• efcdda0176 [diffusion] fix: fix fsdp (#18187) Mick 2026-02-10 20:22:20 +08:00
• 49cbb469b4 [NPU] [CI] Enable run multimodal NPU CI when changes only in multimodal_gen (#18523) Makcum888e 2026-02-10 14:53:43 +03:00
• 47978ee858 [diffusion] feat: support parallel wan-vae decode (#18179) wxy 2026-02-10 18:32:00 +08:00
• 26f2b3798d [DLLM] Basic dLLM scheduling strategy and implementation (#17484) Zehuan Li 2026-02-10 16:54:15 +08:00
• 8da14aea88 [HiCache] fix: StorageMetricsCollector was initialized twice (#18354) shuwenn 2026-02-10 16:53:00 +08:00
• d94d0af573 [AMD] Turn on aiter-prebuild (#18425) YC Tsengandbingxche 2026-02-10 16:49:35 +08:00
• 398b81f78c Support GlmMoeDsaForCausalLM (#18521) 3 people 2026-02-10 02:20:10 -05:00
• e8a2c13380 Deepseekv32 compatibility with transformers v5 (#18297) 3 people 2026-02-10 01:50:40 -05:00
• 0b15f19927 [EPD] Add notification mechanism to fix server hang and add timeout env var (#18229) siyu 2026-02-10 11:52:54 +08:00
• 1d366f1206 Make bench_one_batch_server compatible for more backends (#18512) maocheng23 2026-02-09 18:36:39 -08:00
• 4a1b50bb2d Fix idle batch predict dtype in spec v2 (#18379) Qiaolin Yu 2026-02-09 18:29:13 -08:00
• df733c5ee5 [HiCache][PP] add test case for compatibility (#16395) Teng Ma 2026-02-10 10:03:04 +08:00
• 2825f5d8e0 Tiny fix wrong metric collect key name forward_prefill -> forward_extend (#18506) Liangsheng Yin 2026-02-09 16:23:41 -08:00
• 26a006e47f Add cache_config_info metric. (#17273) Kartik Ramesh 2026-02-09 18:09:09 -06:00
• 54589a2f2d docs: expand and update modelopt documentation (#18479) 3 people 2026-02-09 15:09:52 -08:00
• b027c5aca6 [Auto Sync] Update cache_init_params.py (20260209) (#18502) 4 people 2026-02-09 14:49:41 -08:00
• ce95f203b0 [Auto Sync] Update logits_processor.py (20260209) (#18503) Lianmin Zhengandgithub-actions[bot] 2026-02-09 14:33:02 -08:00
• 01e3f4682e feat(kv-events): Add medium field to KV event types for storage tier tracking (#18205) ishandhanani 2026-02-09 14:39:15 -06:00
• 316f9cbb35 [AMD] add amd ci monitor (#17476) 3 people 2026-02-10 01:04:54 +08:00
• 27c447653d model: support Qwen3.5 (#18489) Zheng Liand瑀澈 2026-02-10 00:27:59 +08:00
• 0b4d4f2838 Fix MMLU benchmark to auto-download data and resolve path issue (#18486) Xinyuan Tong 2026-02-09 10:40:40 -05:00
• 006da22268 Pass quantize_config to _initialize_model (#18273) Kurt Shuster 2026-02-09 07:34:42 -08:00
• ddbcfbaaab feature: support bidirectional attention for Gemma-3 (#10707) brimon 2026-02-09 23:17:45 +08:00
• 4f7da5ad0f [diffusion] chore: fix unclean shutdown and resource leaks (#18477) Mick 2026-02-09 22:32:08 +08:00
• 76eb1c8406 [diffusion] feat: add ModelScope support (#17924) yrk111222 2026-02-09 19:23:45 +08:00
• 615a02dcd4 Revert "optimize get_topk_ragged by fusing get k and k_scale triton kernel" (#18471) Baizhou Zhang 2026-02-09 16:37:19 +08:00
• 875ad6cf35 Tiny rename for spec related fileds. (#18468) Liangsheng Yin 2026-02-09 00:10:39 -08:00
• 107958a489 Make compressed-tensors MoEs support ignored layers (#17828) 3 people 2026-02-09 14:37:33 +08:00
• 14652243bd [DLLM] Add JointThreshold algorithm for joint M2T and T2T decoding (#18171) Junlin ZhouandTiwei Bie 2026-02-09 14:20:45 +08:00
• 28717e3d28 [AMD] CI - Fix AMD daily image release and install dependency (#18452) YC TsengandBingxu Chen 2026-02-09 14:20:09 +08:00
• 3f3c201243 [AMD] Update aiter to v0.1.10.post2 (#18423) 3 people 2026-02-09 14:08:24 +08:00
• b564dcec61 fix: use --no-build-isolation for human-eval install (#18455) Hudson Xing 2026-02-08 21:48:03 -08:00
• a1189068fa fix: fix the wrong return value type of draft model runner (#18105) Yingchun LaiandLiangsheng Yin 2026-02-09 12:51:35 +08:00
• 68e31a3485 [BugFix][PD]Fix metadata_buffer_index leak when aborted in PD (#17483) Zheng Wengang 2026-02-09 11:34:29 +08:00
• bffd765417 Refactoring Mooncake TE as a shared distributed component (#17810) Shangming Cai 2026-02-09 10:53:11 +08:00
• bf89cc3803 [ModelOPT] Support Qwen 3 Next Coder NVFP4 (#18224) Yi Zhong 2026-02-08 17:29:07 -05:00
• 75997ebe8d Update author information in pyproject.toml (#18453) Lianmin Zheng 2026-02-08 12:22:55 -08:00
• 071bf2ce09 [Kimi-K2.5] Fix missing quant_config in KimiK25 (#18440) Mohammad Miadh Angkad 2026-02-09 04:02:45 +08:00
• 656a3d742e Add tensor parallelism support to LFM2 ShortConv layers (#17777) Piotr Mazurek 2026-02-08 17:52:47 +01:00
• 6601bc24da [diffusion] chore: revise process title (#18446) Mick 2026-02-09 00:14:06 +08:00
• 031a652b93 Fix TRT-LLM MLA backend applying k_scale to BF16 KV cache in BMM1 (#18396) debo3 2026-02-08 07:11:16 -08:00
• a41aff1243 [diffusion] refactor: group component loaders under the component_loaders/ directory (#18438) Mick 2026-02-08 23:02:27 +08:00
• ca36d88fa6 [ModelOpt] Fix broken Qwen3-235B-A22B-Instruct-2507-NVFP4 launch (#18189) Yi Zhong 2026-02-08 09:35:28 -05:00
• 43eecd8265 [diffusion] feat: support efficient sequence shard (#18161) wxy 2026-02-08 21:09:39 +08:00
• f600965b0e [CI] fix: notebook ci may not working (#18417) shuwenn 2026-02-08 14:26:35 +08:00
• d71ccd8860 fix: sync server_args.kv_cache_dtype when detecting FP8 KV cache (#18394) Zack Yu 2026-02-07 22:10:59 -08:00
• 8e2e835c2f [Fix] Fix backend selection after flashinfer version update (#18364) DarkSharpness 2026-02-08 11:20:41 +08:00
• 00248d85c7 [diffusion] platform: support WAN/FLUX/Qwen-Image/Qwen-Image-edit on Ascend (#13662) 6 people 2026-02-08 05:45:30 +03:00
• 7b83659310 fix: fix NVFP4 Kimi-K2.5 weight mapping and exclude list (#18370) Mohammad Miadh Angkad 2026-02-08 10:23:48 +08:00
• 64950d8f97 [diffusion] feat: support saving videos directly on the server to avoid the overhead of tensor transfer (#18253) wxy 2026-02-07 22:08:42 +08:00
• 31d4cd2ffd [diffusion] fix: respect dist_timeout option (#18386) Mick 2026-02-07 20:56:04 +08:00
• fddef76619 [Doc] Fix outdated --fp4-gemm-backend documentation (#18350) Mohammad Miadh Angkad 2026-02-07 20:42:47 +08:00
• d792aa7618 [diffusion] fix: remove unnecessary norm_type argument from GLM-Image dits (#18382) Hao JinandHao Jin 2026-02-07 04:35:12 -08:00
• eb4cf1dfc4 [CI] Skip some flaky subtests for test_multi_lora_backend.py (#18408) Baizhou Zhang 2026-02-07 19:06:53 +08:00
• c47c2f9466 [Doc] Update CUDA 13 install guide to install torch first (#18404) Mohammad Miadh AngkadandBaizhou Zhang 2026-02-07 18:04:37 +08:00
• 52401bec1d chore: bump mooncake version to 0.3.9 (#18316) Shangming Cai 2026-02-07 17:30:01 +08:00
• baec650462 [Diffusion] Apply fused_norm_scale_shift to LTX2/MOVA (#18257) Xiaoyu Zhangandyihanc 2026-02-07 17:28:42 +08:00
• e834b85ab6 [NPU] update npu doc (#18344) Hexq0210 2026-02-07 16:38:05 +08:00
• 1552aab741 Support execute_shell_command for env var support (#18390) 赵晨阳 2026-02-06 20:33:29 -08:00
• 4637970dfb [Qwen3Next] Optimize fused_sigmoid_gating_delta_rule_update_kernel (#18271) hlu1 2026-02-06 19:59:42 -08:00
• 9fbec79906 Revert "[Build] Enable full kernel in aarch64 wheel" (#18385) Baizhou Zhang 2026-02-07 09:19:07 +08:00
• bedade1ef0 Merge stage-c-test-large-4-gpu suites into partitioned suites (#18325) Alison Shao 2026-02-06 15:32:33 -08:00
• f1ff697494 add hybrid model PD to NIXL connector (#16229) Neal Vaidyaandishandhanani 2026-02-06 15:05:36 -08:00
• c850a8a41a [Docs] Add Falcon H1, Hunyuan-Large, Qwen3-Omni support and update Diffusion usage (#17888) 6 people 2026-02-07 02:47:51 +05:30
• f2e0048d06 Add CI permission for Shunkangz, dongjiyingdjy, samuellees (#18377) Baizhou Zhang 2026-02-07 01:19:02 +08:00
• e13b727e92 [diffusion] CI: update perf baseline (#17512) Prozac614 2026-02-07 00:28:44 +08:00