Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• 672eb37534 [CPU][Fix CI] Solidate torch version for sgl-kernel-cpu and fix device orientation error (#17460) Zaili Wang 2026-01-22 14:04:50 +08:00
• e2d33531f3 [Kernel] Little refactor of flashinfer allreduce norm fusion (#17474) Baizhou Zhang 2026-01-22 13:31:57 +08:00
• 71482dd171 [diffusion] feat: enable passing Cache‑DiT config for diffusers backend (#16662) Chi McIsaacandMick 2026-01-22 00:13:34 -05:00
• 17807caf82 [AMD] fix amd ci dpskv32 (#17432) YC Tsengandmichaelzhang-ai 2026-01-22 12:34:24 +08:00
• fafa171529 [hotfix] Fixes on cuda 13 docker image (#17541) Baizhou Zhangandiforgetmyname 2026-01-22 12:29:55 +08:00
• a5bbcda968 fix: prefer to use max_completion_tokens rather than max_tokens (#17516) Yingchun Lai 2026-01-22 12:22:20 +08:00
• e95668abc7 [NVIDIA] Fix CUDA arch requirement in nvfp4 cast (#12581) Serge PanevandFan Yin 2026-01-22 05:21:11 +01:00
• 3373545b9f [HotFix]Fix dtype mismatch in nsa indexer on AMD device (#17518) Baizhou Zhang 2026-01-22 12:17:02 +08:00
• d6e2b88288 Add Liquid Foundation Model (LFM2) (#16890) Piotr Mazurek 2026-01-22 04:11:20 +01:00
• f2ae066a6b Update release-branch-cut.yml for actions: write (#17539) Kangyan-Zhou 2026-01-21 18:03:27 -08:00
• 0c2993eed0 Optimize Qwen3-VL video memory usage (#16366) cen121212 2026-01-22 09:10:08 +08:00
• 590969ee9c [Diffusion] Support select fa2 backend in hopper (#17514) Xiaoyu Zhang 2026-01-22 08:23:53 +08:00
• e6ccb2949b Increase wait-for-stage timeouts to handle long queue times (#17536) Alison Shao 2026-01-21 16:10:52 -08:00
• d6ea2c529c Fix import path for UnquantizedLinearMethod in test (#17529) Alison Shao 2026-01-21 15:34:02 -08:00
• 9be2a3a9a3 Remove test_gpt_oss_4gpu.py from __not_in_ci__ (keep in per-commit-4-gpu) (#17534) Alison Shao 2026-01-21 15:31:03 -08:00
• b74a57a8d9 [Auto Sync] Update detokenizer_manager.py, io_struct.py, mu... (20260120) (#17442) 3 people 2026-01-21 14:48:32 -08:00
• 95f59c13fd [Chore] include all jit files in building packages (#17493) DarkSharpness 2026-01-22 06:48:02 +08:00
• 85d9af51da Temporarily disable flaky test_gpt_oss_4gpu.py on B200 (#17528) Alison Shao 2026-01-21 14:01:04 -08:00
• 858f317f13 ci(codespell): centralizes list of ignorable words (#17524) Jacob Gordon 2026-01-21 14:29:14 -06:00
• cf89351691 [new-model] Add support for Cohere2ForCausalLM behind Command-A and Command-R Models (#16927) Lingjun Wen 2026-01-21 12:28:33 -08:00
• 1fdf5cac39 [Auto Sync] Update environ.py, fp8.py (20260121) (#17486) 3 people 2026-01-21 12:04:09 -08:00
• cda43ffa4d ci: avoids duplication of codespell config (#17519) Jacob Gordon 2026-01-21 14:02:37 -06:00
• 390898545e [Misc] Fix argument help string formatting (#17416) Yunmeng 2026-01-22 01:25:32 +08:00
• b827e9d381 [AMD] CI - Fix sgl-kernel unittest (#17490) YC Tseng 2026-01-22 01:23:28 +08:00
• d725487dc8 Disable swa memory for gpt-oss with spec (#17517) Ke Bao 2026-01-22 01:04:19 +08:00
• a95c9f5b81 [NPU] Remove paged attention & Change fia to default attention (#17394) 4 people 2026-01-21 23:58:25 +08:00
• 19089aa431 [Diffusion] Refactor diffusion is_cuda check (#17498) Xiaoyu Zhang 2026-01-21 23:02:24 +08:00
• 4f6f5d25c8 Support fa4 decoding (#16034) Qiaolin Yu 2026-01-21 06:54:02 -08:00
• 458fe5a337 [docs] Show user the fastAPI docs available (#17510) Yi Zhong 2026-01-21 09:26:25 -05:00
• 2ff0880a0e [Fix] GLM 4.7 + NVFP4 + MTP (#17166) b8zhong 2026-01-21 05:34:18 -08:00
• 2c1b164a92 [diffusion] improve: skip negative prompt encoding when guidance_scale <= 1.0 or negative_prompt is None (#16919) Zhu Yuhua 2026-01-21 20:01:55 +08:00
• bcc6d84f93 Use fused_sigmoid_gating_delta_rule_update_kernel for KDA (#17108) strgrb 2026-01-21 19:24:29 +08:00
• a618202fc7 Tiny refine swa kv cache free (#17417) Ke Bao 2026-01-21 19:20:05 +08:00
• 7520b92927 Support EPD error handling (#16670) siyuandZhengWG 2026-01-21 18:47:00 +08:00
• e7224e9681 [diffusion] fix: fix the LoRA weights mismatch caused by weights packing (#17355) Fan Lin 2026-01-21 18:17:16 +08:00
• e776239afd [diffusion] feat: support SageSparseLinearAttention attention backend (#17399) HuangJi 2026-01-21 18:13:51 +08:00
• 1b97fa769b [BUGFIX] fix value oom in radix tree (#17400) Yi Zhang 2026-01-21 17:12:57 +08:00
• 236772c0e1 [RadixTree][2/N Refactor]: swa cache init tiny refactor (#17397) Yi Zhang 2026-01-21 15:48:30 +08:00
• 0d49b13fdd Fix circular import in quantization modules (#17372) Sam Shleifer 2026-01-21 02:47:09 -05:00
• 0a7a2017a0 [diffusion] refactor: refactor and simplify teacache for cachabledit and wanvideo (#16396) 5 people 2026-01-21 15:42:45 +08:00
• 0a9099e137 update ascend docs (#17457) amote-i 2026-01-21 15:36:26 +08:00
• 0050c476fd Add job-level timeout for weekly test workflow (#17462) Alison Shao 2026-01-20 22:45:39 -08:00
• 8251a74d5f [Tiny] Backward compatibility for fp4 gemm flags (#17466) Baizhou Zhang 2026-01-21 14:34:40 +08:00
• a54d75bf2e [Fix] Set fa3 as default MHA backend on Hopper (#17425) Baizhou Zhang 2026-01-21 13:54:09 +08:00
• 3321eb4efa Fix pr-test-finish to fail when wait-for-stage jobs fail (#17465) Alison Shao 2026-01-20 20:50:27 -08:00
• be5121b452 Fix NSA indexer in the nightly test (#17452) Kangyan-Zhou 2026-01-20 19:58:13 -08:00
• c3f9c30f99 [Minor] Change lora_target_modules to "all" in CI tests (#17386) Baizhou Zhang 2026-01-21 11:46:36 +08:00
• 54a821794e [diffusion] fix: fix the bug of output_path not taking effect when generate (#17293) Fan Lin 2026-01-21 11:39:51 +08:00
• aca354bcb3 [NPU] remove features supported on Ascend NPU (#17455) khalilzhk 2026-01-21 11:00:04 +08:00
• aea57b33c6 [scheduler] Clear MM data of finished batch (#17251) Yinghai LuandKangyan-Zhou 2026-01-20 17:45:38 -08:00
• 823a046e8f Add hybrid parallelism test to nightly CI (#17444) Alison Shao 2026-01-20 17:43:50 -08:00
• 648aab0ce3 Fix wait-for-stage jobs running when call-gate fails (#17443) Alison Shao 2026-01-20 17:40:05 -08:00
• 1e309030e3 update urllib3 and gpgv Dockerfile (#17439) ishandhanani 2026-01-20 16:47:20 -06:00
• 6092721594 [Piecewise] Fix PCG issue for multimodal and embedding model that wraps language_model (#17290) Binyao Jiang 2026-01-20 14:06:06 -08:00
• 38c233fd04 [Piecewise] Support PCG weak_ref_tensor cuda kernel on AMD (#17291) Binyao Jiang 2026-01-20 14:05:32 -08:00
• 20ed3822bb [Auto Sync] Update piecewise_cuda_graph_runner.py (20260119) (#17313) 3 people 2026-01-20 14:05:05 -08:00
• 4ecd9afde9 [Docs] Rename SGLang Router to SGLang Model Gateway (#17436) zijiexia 2026-01-20 12:31:10 -08:00
• eb38d64413 [Docs] Explain CUDA attention backend choices and aiter FP8 KV cache support (#17428) Ruihuan He 2026-01-20 14:10:36 -05:00
• 6ea491e439 Overlap shared experts with deepep dispatch for single batch overlap on Blackwell (#17289) Baizhou Zhang 2026-01-21 02:56:55 +08:00
• 16802fb6b2 [FIX] fix mambaish model pp kv cache compute (#17334) GuoweiWangU 2026-01-20 23:59:05 +08:00
• d97066d209 Use attn_tp_group for all reduce in token embedding (#17403) Ke Bao 2026-01-20 23:56:21 +08:00
• ce2d686e94 Disable swa memory for trtllm-mha backend (#17429) Ke Bao 2026-01-20 23:55:00 +08:00
• 76b06bee03 [New Model] GLM4.7-Flash (#17247) 5 people 2026-01-20 07:44:16 -08:00
• 612026ad2c [OPT] DeepSeekV3.2: optimize indexer weight_proj-mma performance (#17205) BingjiaWang 2026-01-20 23:09:44 +08:00
• 55c616427d Add flag that enables NCCL mlp sync batch for overlap scheduler (#17288) Baizhou Zhang 2026-01-20 23:06:55 +08:00
• 91a4cd8648 Update default attn backend to fa3 for mimo model (#17419) Ke Bao 2026-01-20 21:22:27 +08:00
• 23d765d1f2 [Doc] Update pipeline parallelism documentation (#17414) Shangming Cai 2026-01-20 20:10:56 +08:00
• db2425a00b [Fix]: correctly fetch ds32 config in tuning_fused_moe_triton (#17409) Julian Huangand墨楼 2026-01-20 20:08:28 +08:00
• 603f386c6b update docs of Ascend plateform (#17358) amote-i 2026-01-20 19:31:23 +08:00
• f7a5e425c3 [3/N] Achieve fault tolerance at the DP level (#11657) 3 people 2026-01-20 18:47:08 +08:00
• d50dcd9b61 fix: Release pr pypi fix (#17382) Douglas Yang 2026-01-19 23:00:54 -08:00
• e6b7c04947 [Kimi-Linear] Refactor kimi-linear gate calculation to avoid duplicated code (#17160) Yuan Luoandluoyuan.luo 2026-01-20 14:29:24 +08:00
• a3addd6203 [AMD] Add DeepSeek-V3.2 and VLMs model in nightly tests (#17179) 4 people 2026-01-19 20:31:56 -08:00
• 6988a0f570 Disable mla persistent kernel when not using fp8 kv_cache (#17327) Thomas Wang 2026-01-20 12:29:54 +08:00
• 1b192cf198 [NPU] Update NPU doc for model and features supported (#17385) Hexq0210 2026-01-20 12:28:06 +08:00
• c560e14216 [diffusion] fix: enforce 16-pixel alignment for flux2 to prevent shape mismatch crash (#17302) Ratish P 2026-01-20 09:33:33 +05:30
• 71cb9d0302 [PD] Fix PP dynamic chunking with DP attention (#17339) Shangming Cai 2026-01-20 11:27:13 +08:00
• 8fb45523f3 feat: support bitsandbytes quantization algorithm (#15325) shuwenn 2026-01-20 10:36:56 +08:00
• 84aef37808 fix function calling for Trinity (#17364) Raghav Ravishankar 2026-01-20 08:03:17 +05:30
• 17c04b109d Enable parallel stage execution for scheduled CI runs (#16880) Alison Shao 2026-01-19 18:31:46 -08:00
• 55c4288b3e Fix runner utilization workflow to use 24h default (#17378) Alison Shao 2026-01-19 18:31:33 -08:00
• 9f8b79f16f [Docs] Fix formatting in Evaluating New Models with SGLang (#17376) zijiexia 2026-01-19 18:22:30 -08:00
• 7dc3cbe7ca [Docker] Fix CUDA 13 installing wrong nvidia-nccl-cu13 due to nixl-cu13 not breaking system package (#17370) b8zhong 2026-01-19 17:52:30 -08:00
• 79ddc34c1c [Docs] Add new model evaluation docs (#17043) 3 people 2026-01-19 16:35:03 -08:00
• 09a9d214f7 Pipe customized_info through CudaGraphRunner output (#17088) Aurick Qiao 2026-01-19 15:48:49 -08:00
• 7e40d52635 Move test_autoround.py to stage-b-test-large-1-gpu suite (#17336) Alison Shao 2026-01-19 14:36:19 -08:00
• 057b07fc50 Disable unit-test-backend-4-gpu-gb200 job (#17367) Alison Shao 2026-01-19 14:35:58 -08:00
• 91d8c52d6d fix: updating pypi workflow with new base version formatting in pyproject.toml (#17366) Douglas Yang 2026-01-19 13:23:11 -08:00
• e9a44ea607 [AMD] fix perf ci errors (#17363) YC Tseng 2026-01-20 05:04:15 +08:00
• c1282da236 fix(ci): apply MMMU retry logic to all affected test files (#17329) Hudson Xing 2026-01-20 02:00:29 +08:00
• 71279e31f7 [CI] fix test_vlm_models.py (#17049) shuwenn 2026-01-20 02:00:00 +08:00
• 1a053a810c [AMD] CI - add partitions for stage-b-test-small-1-gpu-amd (#17345) YC Tseng 2026-01-20 00:16:07 +08:00
• 2ea02f0642 [AMD CI] Migrate and Add More Testcases (#17116) Bingxu Chenandyctseng0211 2026-01-20 00:07:39 +08:00
• 20b0523eca [RadixTree][1/N Refactor]: Support unified match_prefix params (#17142) 3 people 2026-01-19 22:39:40 +08:00
• ce8a6ac690 Evict swa kv cache during decoding (#17220) Ke Bao 2026-01-19 22:36:52 +08:00
• ebca5879a1 Fix v32 continue_final_message not work (#16567) ybyang 2026-01-19 21:45:39 +08:00
• cc410a1088 [Diffusion] Apply qknorm to flux2 and apply lightx2v rms_norm_one_pass kernel(without residual) (#17305) Xiaoyu Zhangandgemini-code-assist[bot] 2026-01-19 21:25:33 +08:00
• f374623fa9 [Refactor] Set fp4-gemm-backend=auto on SM100 and rename fp4-gemm-backend with flashinfer_ prefix (#17309) b8zhong 2026-01-19 04:09:07 -08:00
• 5c02217746 Inclusion of nvfp4 blockscale in EPLB Rebalance (#17158) Shu Wang 2026-01-19 03:45:27 -06:00
• 8916b9d080 Migrate performance, accuracy, and quantization tests to CI registry (#17177) Alison ShaoandKangyan-Zhou 2026-01-18 23:25:24 -08:00