Skip to content

Actions: beginlner/vllm

Actions

ruff

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
ruff.yml
23 workflow runs
23 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Speculative decoding 2/9] Multi-step worker for draft model (#2424) ruff #23: Commit 18bfcdd pushed by beginlner
January 22, 2024 02:58 16s main
main
January 22, 2024 02:58 16s
OpenAI Server refactoring (#2360) ruff #22: Commit 14cc317 pushed by beginlner
January 17, 2024 06:03 19s main
main
January 17, 2024 06:03 19s
fix weigit loading for GQA with TP (#2379) ruff #21: Commit f780504 pushed by beginlner
January 16, 2024 02:35 16s main
main
January 16, 2024 02:35 16s
[CI] Add Buildkite (#2355) ruff #20: Commit 6e01e8c pushed by beginlner
January 15, 2024 08:40 17s main
main
January 15, 2024 08:40 17s
Changed scheduler to use deques instead of lists (#2290) ruff #19: Commit 05921a9 pushed by beginlner
January 8, 2024 02:16 19s main
main
January 8, 2024 02:16 19s
Compute logits*v in FP32 in attention kernel to improve numerical acc… ruff #18: Commit d2f5171 pushed by beginlner
January 8, 2024 02:15 23s main
main
January 8, 2024 02:15 23s
Changed scheduler to use deques instead of lists (#2290) ruff #17: Commit 05921a9 pushed by beginlner
January 8, 2024 01:36 28s main
main
January 8, 2024 01:36 28s
Bump up to v0.2.7 (#2337) ruff #16: Commit 2e0b6e7 pushed by beginlner
January 4, 2024 03:31 17s main
main
January 4, 2024 03:31 17s
[BUGFIX] Fix communication test (#2285) ruff #15: Commit 358c328 pushed by beginlner
December 29, 2023 09:00 20s main
main
December 29, 2023 09:00 20s
[BUGFIX] Fix the path of test prompts (#2273) ruff #14: Commit 4aaafdd pushed by beginlner
December 27, 2023 09:13 17s main
main
December 27, 2023 09:13 17s
[BugFix] Fix recovery logic for sequence group (#2186) ruff #13: Commit a1b9cb2 pushed by beginlner
December 22, 2023 03:22 21s main
main
December 22, 2023 03:22 21s
[Docs] Fix broken links (#2222) ruff #12: Commit c17daa9 pushed by beginlner
December 21, 2023 01:42 21s main
main
December 21, 2023 01:42 21s
Make _prepare_sample non-blocking and use pinned memory for input buf… ruff #11: Commit 31bff69 pushed by beginlner
December 20, 2023 03:03 22s main
main
December 20, 2023 03:03 22s
Add warning on CUDA graph memory usage (#2182) ruff #10: Commit 21d5daa pushed by beginlner
December 19, 2023 03:42 18s main
main
December 19, 2023 03:42 18s
Update Help Text for --gpu-memory-utilization Argument (#2183) ruff #9: Commit 290e015 pushed by beginlner
December 19, 2023 01:46 16s main
main
December 19, 2023 01:46 16s
Add SSL arguments to API servers (#2109) ruff #8: Commit 08133c4 pushed by beginlner
December 18, 2023 03:12 21s main
main
December 18, 2023 03:12 21s
[BugFix] Fix input positions for long context with sliding window (#2… ruff #7: Commit f1c8520 pushed by beginlner
December 14, 2023 07:48 21s main
main
December 14, 2023 07:48 21s
Remove max_num_seqs in latency benchmark script (#1855) ruff #6: Commit 51d3cb9 pushed by beginlner
November 30, 2023 09:21 19s main
main
November 30, 2023 09:21 19s
Refactor Attention (#1840) ruff #5: Commit a9e4574 pushed by beginlner
November 30, 2023 00:59 29s main
main
November 30, 2023 00:59 29s
Fix model docstrings (#1764) ruff #4: Commit 7c60044 pushed by beginlner
November 27, 2023 01:08 15s main
main
November 27, 2023 01:08 15s
Add stop_token_ids in SamplingParams.__repr__ (#1745) ruff #3: Commit 094f716 pushed by beginlner
November 22, 2023 05:13 17s main
main
November 22, 2023 05:13 17s
[BugFix] ray.init with num_cpus=32 to prevent stucks when there are many virtual CPUs ruff #2: Pull request #2 opened by beginlner
November 22, 2023 03:27 14s beginlner-patch-1
beginlner-patch-1
November 22, 2023 03:27 14s
[FIX] Fix the case when input_is_parallel=False for `ScaledActivati… ruff #1: Commit 7d761fe pushed by beginlner
November 22, 2023 03:23 20s main
main
November 22, 2023 03:23 20s