Skip to content

Actions: 0xjunhao/vllm

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-commit.yml
18 workflow runs
18 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
[Bugfix][Spec Decode] Honour the draft's attention_backend on Model R… pre-commit #30: Commit 2524051 pushed by 0xjunhao
Skipped main
main
Skipped
[Bugfix] Thread kv_transfer_params into engine for /inference/v1/gene… pre-commit #29: Commit c71f6f8 pushed by 0xjunhao
1d 0h 0m 2s main
main
1d 0h 0m 2s
[Frontend] Preserve bare Inkling text in Python and Rust parsers (#50… pre-commit #28: Commit 629a938 pushed by 0xjunhao
1d 0h 0m 2s main
main
1d 0h 0m 2s
[XPU][CI]Adjust timeout_in_minutes in Intel GPU CI (#48418) pre-commit #27: Commit 93e3bc8 pushed by 0xjunhao
1d 0h 0m 1s main
main
1d 0h 0m 1s
Upgrade tpu-inference to v0.19.0 (#41844) pre-commit #26: Commit ca3e62d pushed by 0xjunhao
5m 16s main
main
5m 16s
[NVFP4] NVFP4 MOE emulation fallback for H100/MI300/MI350, standardiz… pre-commit #25: Commit d622e27 pushed by 0xjunhao
4m 8s main
main
4m 8s
[CI/Build] Improve stability of CPU tests (#39966) pre-commit #24: Commit 324a3d2 pushed by 0xjunhao
5m 31s main
main
5m 31s
[Model] Sync upstream BT=chunk_size fix for GDN chunk_fwd_kernel_o, s… pre-commit #23: Commit b779eb3 pushed by 0xjunhao
4m 30s main
main
4m 30s
[Async][Spec Decoding] Zero-bubble async scheduling + spec decoding (… pre-commit #22: Commit fafe76b pushed by 0xjunhao
3m 13s main
main
3m 13s
[Bugfix] Fix ROCm crash in qwen3_next multi-stream events (#36795) (#… pre-commit #21: Commit a913b61 pushed by 0xjunhao
4m 41s main
main
4m 41s
[UX] Add vLLM model inspection view (#29450) pre-commit #20: Commit d5ec6c0 pushed by 0xjunhao
3m 30s main
main
3m 30s
[ROCM][CI] Fix AMD Examples Test Group (#30276) pre-commit #19: Commit 2cc5aff pushed by 0xjunhao
4m 42s main
main
4m 42s
Re-enable FlashInfer for Llama4 on Blackwell in e2e fusion tests (#28… pre-commit #18: Commit 61728cd pushed by 0xjunhao
4m 39s main
main
4m 39s
[Bug] Fix DeepEP low latency `assert self.batched_router_logits.size(… pre-commit #17: Commit fcb1d57 pushed by 0xjunhao
4m 29s main
main
4m 29s
Use UV_LINK_MODE=copy in Dockerfile to avoid hardlink fail (#22128) pre-commit #16: Commit c494f96 pushed by 0xjunhao
7m 3s main
main
7m 3s
[Bugfix][V1][P/D]Fix the uneven polling issue in the toy proxy for P2… pre-commit #15: Commit c09efff pushed by 0xjunhao
6m 45s main
main
6m 45s
[Bug] Update auto_tune.sh to separate benchmarking and profiling. (#2… pre-commit #14: Commit 309c1bb pushed by 0xjunhao
6m 39s main
main
6m 39s
feat: Add Support GPTQ Quantization MOE on ROCM vllm serve (#21733) pre-commit #13: Commit 3654847 pushed by 0xjunhao
7m 33s main
main
7m 33s