Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• 67e6ef4b2d feat: longcat flash add aux layers capture for eagle3 (#14161) Tianhao Zhou 2025-11-30 00:50:55 -08:00
• 65ba5ab8b1 add cpp files for cpp_radix_tree to pyproject.toml. (#14052) strgrb 2025-11-30 13:05:04 +08:00
• 990023e59b [diffusion] lora: Fix LoRA weight merging for torch.nn.Linear layers from diffusers modules (#14150) WenhaoZhangandniehen6174 2025-11-30 12:44:12 +08:00
• 5ddd2f6b6b Always run model evaluation even if the trace upload step fails (#14157) Kangyan-Zhou 2025-11-29 20:13:59 -08:00
• 0ae4b1ad81 Show errors when misusing env variables (#14154) fzyzcjy 2025-11-30 10:57:35 +08:00
• 94cd64a7b0 Support checking fp8 params in weight_checker (#14147) fzyzcjy 2025-11-30 09:08:59 +08:00
• b870271a50 Fix spec v2 does not support RL update weights from tensor (#14146) fzyzcjy 2025-11-30 09:08:05 +08:00
• 22ee9b0111 Super tiny add more info in dumper (#14145) fzyzcjy 2025-11-30 09:07:39 +08:00
• 9d0e5f1f74 Tiny fix DeepGEMM precompile rank check (#14136) fzyzcjy 2025-11-30 09:07:17 +08:00
• 1d3d8b3418 Fix Minimax M2 loading issue (#13956) Kangyan-Zhou 2025-11-29 14:07:19 -08:00
• 155a9e7237 Fix condition for streaming output_ids in tokenizer manager (#13759) 4 people 2025-11-29 13:56:15 -08:00
• d7cb08c5be Always run all stages in cron based PR tests (#14151) Kangyan-Zhou 2025-11-29 12:32:06 -08:00
• 3339c81072 fix RuntimeError: RMSNorm failed with error code an illegal memory access was encountered (#14135) gongwei-130 2025-11-29 12:17:41 -08:00
• d6c88d519d Trigger PR test on main every 3 hours instead of push event (#14130) Kangyan-Zhou 2025-11-29 10:12:50 -08:00
• f03ea34a3d add runtime check for PyTorch 2.9.1 + CuDNN < 9.15 to prevent Conv3d performance issues (#14119) Yuhao Yang 2025-11-29 23:05:54 +08:00
• 4cafc835d3 Super tiny fix typo (#14131) fzyzcjy 2025-11-29 21:08:31 +08:00
• c6a52f4411 [diffusion] chore: add resolution shortcuts for sampling params (#14129) Mick 2025-11-29 18:00:21 +08:00
• c6d34a0688 Move piecewise cuda graph test to manual dir to fix CI (#14121) Shangming Cai 2025-11-29 16:52:01 +08:00
• 848ee57067 feat: support flashinfer kernel autotune (#12306) 3 people 2025-11-29 16:05:37 +08:00
• ce6b7dfce7 Add auto-tune workflow (#14124) Lianmin Zheng 2025-11-28 23:23:53 -08:00
• 0fe74af563 Remove incorrect deep_gemm assertions from server_args.py (#14113) Cheng WanandKangyan Zhou 2025-11-28 20:25:39 -08:00
• 0a362d653f [diffusion] log: unify generation performance logging (#14117) Mick 2025-11-29 12:21:59 +08:00
• 143b57b805 enable piecewise cuda graph for prefill server (#13377) fjybiocsandserverance.fu 2025-11-29 12:09:26 +08:00
• f446b51c41 fix: malformed KV events for NVIDIA Dynamo (#13488) 3 people 2025-11-28 14:55:20 -08:00
• a102a0507a Disable Deepep 2 GPU tests (#14111) Kangyan-Zhou 2025-11-28 13:56:34 -08:00
• 6bad6a3655 [model-gateway] Add version command support to SMG (#12558) Tony Lu 2025-11-29 04:34:19 +08:00
• 11b6217aee Fix NIXL OBJ desciptors (#10712) Tomer ShmilovichandTomer Shmilovich 2025-11-28 21:32:07 +02:00
• 0b0b2607ca [CPU] Apply uv as package manager (#14106) Zaili Wang 2025-11-29 02:36:53 +08:00
• 841eb29d3d [diffusion] model: support z-image (#14067) Yuhao Yang 2025-11-28 21:48:31 +08:00
• 45cf575852 Fix overlap scheduler not take effect when outputing logprobs (#14096) fzyzcjy 2025-11-28 18:15:56 +08:00
• 0e8ce1e832 [diffusion] refactor: clean useless files (#14094) Mick 2025-11-28 18:14:00 +08:00
• ea1e9f6b3c feat: support qwen3_vl vision model dp (#13724) Lzhang-hub 2025-11-28 17:29:07 +08:00
• f6e37d3edb [Bugfix] qwen2.5-vl spec decode accept_len low (#13904) Lzhang-hubandYuan Luo 2025-11-28 17:26:32 +08:00
• ab9a46d462 Support configuring the request limit per receiving poll (#14076) 3 people 2025-11-28 16:14:21 +08:00
• 621061f017 [Bugfix] input prompt was not logged (#13936) shuwenn 2025-11-28 16:00:51 +08:00
• 7daddcdb58 Fix structural_tag tool call with null schema (#14006) Aleksandr Krotov 2025-11-28 10:04:16 +03:00
• 91d249cd9b fix: small changes to enable test_mrope.py (#14082) Raayan Dhar 2025-11-27 20:58:17 -10:00
• 951028968c [diffusion] refactor: refactor ComponentLoader and support loading native models from diffusers and transformers (#13205) Mick 2025-11-28 14:17:32 +08:00
• 3543a04a48 [diffusion] refactor: refactor condition image resize logic (#14079) Mick 2025-11-28 14:06:34 +08:00
• e12c78aab6 [sgl-kernel][1/2] Fused qk_norm_rope for Qwen3-MoE (#14036) Yuan Luoandluoyuan.luo 2025-11-28 12:25:15 +08:00
• bce40fa217 Fix utils import issue for nightly tests (#13944) alisonshao 2025-11-27 15:24:27 -08:00
• 051ad83347 [chore] Arrange NV packages in Dockerfile (#13749) Baizhou Zhang 2025-11-27 18:08:27 -05:00
• 4c9f7c97d3 Temporarily disabled test (#14069) Kangyan-Zhou 2025-11-27 14:58:46 -08:00
• 63b056213f Remove disused B300 Dockerfile (#13946) Mohammad Miadh Angkad 2025-11-27 22:48:00 +08:00
• 21af8e73ad Super tiny add comments to SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK (#14048) fzyzcjy 2025-11-27 22:16:43 +08:00
• 7ab548ef64 [2/2] Refactor DeepGeem requant for FP8 FusedMoE on Blackwell (#13960) Baizhou Zhang 2025-11-27 09:00:26 -05:00
• bab033b970 Adjust max-parallel for CUDA CI (#14057) Liangsheng Yin 2025-11-27 20:48:37 +08:00
• 6350042696 feat: Naive support Spec V2 + Constrained Decoding (#13425) Yixin DongandLiangsheng Yin 2025-11-27 04:31:46 -08:00
• 25758647b1 Support sanity checking weight consistency especially for RL (#13854) fzyzcjy 2025-11-27 20:25:12 +08:00
• 2bc8ee8b74 Tiny support 3D tensors in inverse_transform_scale_ue8m0 (#14002) fzyzcjy 2025-11-27 20:20:45 +08:00
• ab843ced31 [Feat]Add scheduler recv skipper weights to environment configuration (#13855) Jimmy 2025-11-27 18:16:11 +08:00
• 6edffc6391 [diffusion] perf: improve black-forest-labs/FLUX.2-dev (#14040) Mick 2025-11-27 14:49:52 +08:00
• 077ca70ee4 [Intel XPU]Add xpu support for get_device_memory_capacity (#13895) gaopengff 2025-11-27 12:55:52 +08:00
• 7cb04dc0e5 Use trtllm mha decode kernel for target_verify in speculative decoding (#13976) Qiaolin YuandKangyan-Zhou 2025-11-26 20:40:34 -08:00
• 5443db8759 fix: Fix AMD CI failures with HIP layernorm and PyPI connectivity (#13814) sunxxunsandroot 2025-11-26 22:30:37 -05:00
• 9f340ab1fb [Piecewise] support disable decode cuda graph when enable piecewise cuda graph (#13965) Stefan He 2025-11-26 18:35:59 -08:00
• 70c6f95107 Add CODEOWNERS entry for batch_invariant_ops (#14026) Stefan He 2025-11-26 18:35:37 -08:00
• d941a3befa Fix nightly test failure: NSA indexer dtype (#14017) alisonshao 2025-11-26 18:27:51 -08:00
• b12c9e5c0a Fix installation for nvidia-nvshmem-cu12 (#14033) Cheng Wan 2025-11-26 18:27:12 -08:00
• e9e90460ed [model-gateway] allow refill rate to be zero (#14030) Simo Lin 2025-11-26 17:15:27 -08:00
• 6330d6641b Fix flashinfer cutlass MoE output shape for non-FP4-packed inputs (#14028) alisonshao 2025-11-26 17:09:02 -08:00
• 91e8dc371a [Feat][NVFP4] Enable NVFP4 MoE for Qwen series models (eg. Qwen3-Next) #13761 (#13761) SamandKaixi Hou 2025-11-27 08:53:45 +08:00
• 231df4b0d4 Cleanup server args (#14027) Lianmin Zheng 2025-11-26 16:32:41 -08:00
• b087ef8b4b Nightly test job filter (#14025) alisonshao 2025-11-26 16:04:24 -08:00
• 5155016b56 [feat] update bucketed weights from distributed (#13824) ShawnY112358andStefan He 2025-11-27 07:30:45 +08:00
• 082b54c689 Support nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 (and nvidia/C-RADIOv2-H) (#12277) Netanel Haber 2025-11-27 01:28:52 +02:00
• a8ef4d1804 Add nightly test support to unified run_suite.py (#13941) alisonshao 2025-11-26 15:16:12 -08:00
• 15ff6982b9 Support KTransformers for Qwen3-VL moe (#13983) mrhaoxx 2025-11-27 06:59:15 +08:00
• 9adef42c60 Fix nightly test failure: CPP radix cache init (#14018) alisonshao 2025-11-26 14:58:26 -08:00
• 685b9d82bd fix: cuda graph issue while running longcat_flash (#14007) Tianhao Zhou 2025-11-26 14:57:22 -08:00
• a223402ffb Add adapter_model.safetensors to corruption validation for LoRA (#14022) alisonshao 2025-11-26 14:52:46 -08:00
• 44d0a848da [model-gateway] Fix flaky test_circuit_breaker_half_open_failure_reopens (#14019) Xinyue Zhang 2025-11-26 14:52:10 -08:00
• 5b7da0f58e Temporarily disable test_update_weights_from_disk.py in CI (#14021) alisonshao 2025-11-26 13:56:28 -08:00
• 697a77bf73 Add stress test workflow (#13937) Douglas YangandLiangsheng Yin 2025-11-26 13:24:39 -08:00
• 0a186924ba [Code sync] Fix registration of some ops in grok & Fix oss sync scripts (#13990) Lianmin ZhengandStefan He 2025-11-26 13:11:52 -08:00
• b6312e62ea Update CODEOWNERS for layer and executor files (#14020) Stefan He 2025-11-26 12:59:04 -08:00
• 779cbc6e4b Fix Nvidia nightly test trigger params when it is triggered by parent workflow (#13966) Kangyan-Zhou 2025-11-26 12:01:48 -08:00
• 67c8c86722 [model-gateway][doc] Update transport terminology to protocol in README.md (#13872) Wenyi XuandSimo Lin 2025-11-27 03:44:59 +08:00
• 69a03bc3f7 [ci] allow manual label to trigger ci in rust, change ci order (#14016) Simo Lin 2025-11-26 11:38:50 -08:00
• 66f242b98f [model gateway][grpc] Add tojson filter to override minijinja's tojson (#14013) Chang SuandSimo Lin 2025-11-26 11:05:01 -08:00
• 8a9b8b8457 Revert "Fix nightly test failures: NSA indexer dtype and CPP radix cache init" (#14015) Baizhou Zhang 2025-11-26 10:45:23 -08:00
• 7e964b5198 [ci] mark skip as success instead of failure (#14014) Simo Lin 2025-11-26 10:39:38 -08:00
• a0d9f6cdd8 [model-gateway] fix xpu ci (#14012) Simo Lin 2025-11-26 10:33:59 -08:00
• 8308cd3632 Support internvl on Blackwell (which doesn't support fa3): add SingletonCache support to Vision{Sdpa|Triton|Ascend}Attention (#13151) Netanel Haber 2025-11-26 20:31:45 +02:00
• e0e8a99630 fix: correct usage of minimax-m2 deepep moe forward (#13892) 3 people 2025-11-27 02:01:23 +08:00
• 5102d00901 [diffusion] model: support black-forest-labs/FLUX.2-dev (#14000) Mick 2025-11-27 01:49:40 +08:00
• 0dd759e087 Put pr-gate after check-changes (#14009) Liangsheng Yin 2025-11-27 01:40:16 +08:00
• 5e70880e64 [model-gateway] Add PostgreSQL support to binding (#13766) 4 people 2025-11-27 01:11:13 +08:00
• 9dab534b35 fix spec dec request level metrics (#13754) Vedant V JhaveriandLiangsheng Yin 2025-11-26 09:09:21 -08:00
• 262c3c1fde [Ascend] Support enable-mixed-chunk in non-MLA scenarios (#12491) Michelle Wuandronnie_zheng 2025-11-26 08:00:21 -08:00
• 6c190cbda0 Rename: --hooks to --forward-hooks (#13994) Liangsheng Yin 2025-11-26 22:26:28 +08:00
• eff6a07c8f Fix get_load API (#13991) Liangsheng Yin 2025-11-26 22:07:51 +08:00
• b704b0a922 Optimize uneven PP layer distribution logic to improve PP performance (#13977) Shangming Cai 2025-11-26 22:05:03 +08:00
• 15729dbc8e Use dynamically maintained num_waiting_tokens in get_load() (#13203) vipwangerxiaoandPeng Wang 2025-11-26 20:34:45 +08:00
• 21b0582d4b [feature] Initial block diffusion language model support (#12588) Zehuan LiandTiwei Bie 2025-11-26 17:57:54 +08:00
• 5795da5e83 [diffusion] fix: fix the issue where the qwen-edit & wan model produces incorrect output during sequence parallelism (#13922) Yuhao Yang 2025-11-26 15:58:23 +08:00
• 540d6fee20 Support piecewise CUDA graph for embedding models (#13852) StonyPortandqiuxuan.lzw 2025-11-26 15:29:46 +08:00
• 5a8adca900 Turn off PREBUILD aiter in MI355 (#13963) Thomas Wang 2025-11-26 14:30:39 +08:00
• 007c3e234c [feat] support in-flight weight update (#10071) ShawnY112358and赵晨阳 2025-11-26 14:03:13 +08:00
• 7130ad3a29 Fix SGLANG_ENABLE_HEALTH_ENDPOINT_GENERATION not working (#13961) fzyzcjy 2025-11-26 13:58:55 +08:00