Skip to content

Actions: hao-aaron/vllm

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-commit.yml
41 workflow runs
41 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[K3 Perf] Fuse MXFP4 top-k finalization into latent-tail, ~5% E2E lat… pre-commit #41: Commit 7a2fdba pushed by hao-aaron
1d 0h 0m 3s main
main
1d 0h 0m 3s
[Attention] Fix FlashInfer SM12x prefill with sinks (#52148) pre-commit #40: Commit b652ded pushed by hao-aaron
1d 0h 0m 1s main
main
1d 0h 0m 1s
[ROCm][DistInf] Enable vLLM DI CI with buildkite/slurm (#47030) pre-commit #39: Commit 1482d2e pushed by hao-aaron
1d 0h 0m 2s main
main
1d 0h 0m 2s
[Bugfix] Shard UniformTypeKVCacheSpecs block table width under DCP (#… pre-commit #38: Commit f0de1a6 pushed by hao-aaron
1d 0h 0m 2s main
main
1d 0h 0m 2s
[copy of #45208] CuMem slept-L1 fragmentation accounting (#49208) pre-commit #37: Commit 58b2012 pushed by hao-aaron
1d 0h 0m 2s main
main
1d 0h 0m 2s
[Bugfix][GLM4V] Fix video dummy profiling and memory usage (#48729) pre-commit #36: Commit bf578e1 pushed by hao-aaron
1d 0h 0m 2s main
main
1d 0h 0m 2s
[CI] Remove torch_nightly mirror tags (superseded by TORCH_NIGHTLY fu… pre-commit #35: Commit e91f5f8 pushed by hao-aaron
1d 0h 0m 1s main
main
1d 0h 0m 1s
[Feat] Improve Triton JIT diagnostics (#46621) pre-commit #34: Commit 20434c4 pushed by hao-aaron
1d 0h 0m 2s main
main
1d 0h 0m 2s
[Speculative Decoding] Propagate norm_output and fc_norm config for E… pre-commit #33: Commit dda3aca pushed by hao-aaron
1d 0h 0m 2s main
main
1d 0h 0m 2s
[CI] Fix CPU-Multi-Modal Model Tests timeout by adding a 4th shard (#… pre-commit #32: Commit e2fe837 pushed by hao-aaron
1d 0h 0m 2s main
main
1d 0h 0m 2s
Fix sparse NCCL weight transfer test construction (#44345) pre-commit #31: Commit 0917a00 pushed by hao-aaron
4m 11s main
main
4m 11s
[Misc] Remove stray empty file (#44350) pre-commit #30: Commit 5577811 pushed by hao-aaron
5m 38s main
main
5m 38s
[Frontend][Core] Add sparse NCCL weight transfer support for in-place… pre-commit #29: Commit 266b9d9 pushed by hao-aaron
4m 4s main
main
4m 4s
[Rust Frontend] Add reasoning/tool parser & renderer roundtrip tests … pre-commit #28: Commit 0b68f21 pushed by hao-aaron
3m 37s main
main
3m 37s
[bug] fix WeightTransferConfig.backend to allow for all strings (#43121) pre-commit #27: Commit 73dd2f3 pushed by hao-aaron
4m 8s main
main
4m 8s
Add VLLM_USE_SPINLOOP_EXT to use more efficient busy polling (#36517) pre-commit #26: Commit 39dff5f pushed by hao-aaron
4m 16s main
main
4m 16s
[CI][Elastic EP] Fix Elastic EP Scaling Test Failure (#41792) pre-commit #25: Commit 44e6b44 pushed by hao-aaron
5m 25s main
main
5m 25s
[DSV4] Add knob to enable pre-attn gemm (#41443) pre-commit #24: Commit bcf5cac pushed by hao-aaron
5m 18s main
main
5m 18s
[MoE] Move DEEP_GEMM into experts/ subdirectory (#39005) pre-commit #23: Commit a776a48 pushed by hao-aaron
4m 27s main
main
4m 27s
[MoE Refactor][Test] FusedMoE layer test (#24675) pre-commit #22: Commit f014824 pushed by hao-aaron
3m 20s main
main
3m 20s
[Compile] Fix nvfp4 compile warning (#38573) pre-commit #21: Commit c9a9db0 pushed by hao-aaron
4m 19s main
main
4m 19s
[torch.compile][BE][Multimodal] Remove requirement to set_model_tag t… pre-commit #20: Commit 7769b58 pushed by hao-aaron
3m 8s main
main
3m 8s
[Kernel] Add non-gated support for NVFP4 CUTLASS MoE (#37320) pre-commit #19: Commit 09e4576 pushed by hao-aaron
4m 23s main
main
4m 23s
[ROCm][Quantization] add quark w4a8 mxfp4_fp8 for LinearLayer (#35316) pre-commit #18: Commit 6341d43 pushed by hao-aaron
3m 6s main
main
3m 6s
[Feature]: Remove Chunking From FusedMoE (#34086) pre-commit #17: Commit 2cdf922 pushed by hao-aaron
4m 16s main
main
4m 16s