Skip to content

Actions: Pradyun92/vllm

Actions

pre-commit

Actions

Loading...
Loading

Show workflow options

Create status badge

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

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Supress verbose logs from model_hosting_container_standards (#28949) pre-commit #20: Commit 67745d1 pushed by Pradyun92
4m 27s main
main
4m 27s
[Bugfix] Ensure calculated KV scales are applied in attention. (#27232) pre-commit #19: Commit a5a790e pushed by Pradyun92
4m 32s main
main
4m 32s
[Chore] Separate out vllm.utils.platform_utils.py (#27374) pre-commit #18: Commit ca76486 pushed by Pradyun92
4m 41s main
main
4m 41s
[LoRA] LoRA cuda graph specialization (#25914) pre-commit #17: Commit b63f214 pushed by Pradyun92
3m 17s main
main
3m 17s
[Chore] Separate out hashing utilities from vllm.utils (#27151) pre-commit #16: Commit 8a29711 pushed by Pradyun92
3m 20s main
main
3m 20s
[Test] Make test_failure more stable for batch invariance (#27054) pre-commit #15: Commit f50cc22 pushed by Pradyun92
4m 19s main
main
4m 19s
Refactor Transformers backend to use mixins (#26906) pre-commit #14: Commit fb5e10d pushed by Pradyun92
3m 15s main
main
3m 15s
[Qwen3-Next] Add tuned MoE config for Qwen3-Next FP8 on H100 tp2 (#26… pre-commit #13: Commit f96bc36 pushed by Pradyun92
4m 9s main
main
4m 9s
[Bugfix] Allow --skip-tokenizer-init with `echo and return_token_id… pre-commit #12: Commit a964e5e pushed by Pradyun92
4m 44s main
main
4m 44s
[BugFix][DP/EP] Fix CUTLASS MLA hang under load (#26026) pre-commit #11: Commit 1726e93 pushed by Pradyun92
4m 57s main
main
4m 57s
[BugFix][torch.compile] KV scale calculation issues with FP8 quantiza… pre-commit #10: Commit c42ff4f pushed by Pradyun92
4m 53s main
main
4m 53s
[VLM] Update Qwen3-VL max_num_video_tokens calculation for configurab… pre-commit #9: Commit 0efd540 pushed by Pradyun92
4m 37s main
main
4m 37s
[Misc] Simplify test_argsort_mm_positions (#25690) pre-commit #8: Commit 6b0fcbb pushed by Pradyun92
6m 15s main
main
6m 15s
[Benchmarks] Throw usage error when using dataset-name random and dat… pre-commit #7: Commit ff68035 pushed by Pradyun92
7m 9s main
main
7m 9s
fix type of sampling rate for encode_base64 (#24826) pre-commit #6: Commit 1177dd5 pushed by Pradyun92
7m 5s main
main
7m 5s
[Model] Add Olmo3 model implementation (#24534) pre-commit #5: Commit 89e08d6 pushed by Pradyun92
7m 6s main
main
7m 6s
[Model] Switch to Fused RMSNorm in GLM-4.1V model (#24733) pre-commit #4: Commit f17c075 pushed by Pradyun92
7m 39s main
main
7m 39s
[Spec Decode] Fix offline spec_decode.py (#24257) pre-commit #3: Commit 41183c1 pushed by Pradyun92
8m 11s main
main
8m 11s
Tuned H100/H200 triton fp8 block configs for fused_qkv_a_proj (#23939) pre-commit #2: Commit b7adf94 pushed by Pradyun92
8m 31s main
main
8m 31s
[Bugfix][CI/Build][ROCm] Make sure to use the headers from the build … pre-commit #1: Commit 5d5d419 pushed by Pradyun92
8m 23s main
main
8m 23s