Skip to content

Actions: megha95/vllm

clang-format

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
28 workflow runs
28 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Core/Bugfix] Add query dtype as per FlashInfer API requirements. (#8…
clang-format #28: Commit e39ebf5 pushed by megha95
September 5, 2024 06:04 20s main
September 5, 2024 06:04 20s
Bump version to v0.6.0 (#8166)
clang-format #27: Commit 32e7db2 pushed by megha95
September 4, 2024 23:37 19s main
September 4, 2024 23:37 19s
[Core] Optimize Async + Multi-step (#8050)
clang-format #26: Commit 6d646d0 pushed by megha95
September 3, 2024 18:59 18s main
September 3, 2024 18:59 18s
[TPU][Bugfix] Fix tpu type api (#8035)
clang-format #25: Commit 2684efc pushed by megha95
August 30, 2024 19:39 20s main
August 30, 2024 19:39 20s
[Core][Kernels] Enable FP8 KV Cache with Flashinfer backend. + BugFi…
clang-format #24: Commit 6b34215 pushed by megha95
August 29, 2024 18:55 19s main
August 29, 2024 18:55 19s
August 28, 2024 17:16 26s
[Bugfix][VLM] Fix incompatibility between #7902 and #7230 (#7948)
clang-format #22: Commit ef9baee pushed by alexm-neuralmagic
August 28, 2024 15:24 22s main
August 28, 2024 15:24 22s
[Doc] fix the autoAWQ example (#7937)
clang-format #21: Commit 98c12cf pushed by alexm-neuralmagic
August 28, 2024 13:16 23s main
August 28, 2024 13:16 23s
August 27, 2024 13:19 18s
[ci][test] fix RemoteOpenAIServer (#7838)
clang-format #19: Commit aab0fcd pushed by alexm-neuralmagic
August 24, 2024 19:30 20s main
August 24, 2024 19:30 20s
August 24, 2024 12:43 18s
[Bugfix] Fix run_batch logger (#7640)
clang-format #17: Commit 6885fde pushed by megha95
August 23, 2024 21:25 17s main
August 23, 2024 21:25 17s
[BugFix] Fix server crash on empty prompt (#7746)
clang-format #16: Commit e25fee5 pushed by alexm-neuralmagic
August 23, 2024 13:41 21s main
August 23, 2024 13:41 21s
August 22, 2024 15:52 15s
August 22, 2024 01:30 14s
August 20, 2024 13:31 18s
[Bugfix] support tie_word_embeddings for all models (#5724)
clang-format #12: Commit f4fc733 pushed by megha95
August 20, 2024 05:13 19s main
August 20, 2024 05:13 19s
[Bugfix] Don't disable existing loggers (#7664)
clang-format #11: Commit da11523 pushed by megha95
August 19, 2024 22:18 15s main
August 19, 2024 22:18 15s
[Misc] Remove Gemma RoPE (#7638)
clang-format #10: Commit df845b2 pushed by megha95
August 19, 2024 16:54 19s main
August 19, 2024 16:54 19s
[Misc] Use scalar type to dispatch to different gptq_marlin kernels…
clang-format #9: Commit 6aa33cb pushed by megha95
August 12, 2024 20:01 15s main
August 12, 2024 20:01 15s
bump version to v0.5.4 (#7139)
clang-format #8: Commit 4db5176 pushed by megha95
August 5, 2024 22:56 20s main
August 5, 2024 22:56 20s
[Bugfix] Allow vllm to still work if triton is not installed. (#6786)
clang-format #7: Commit 9a7e2d0 pushed by megha95
July 29, 2024 23:27 18s main
July 29, 2024 23:27 18s
[TPU] Reduce compilation time & Upgrade PyTorch XLA version (#6856)
clang-format #6: Commit fad5576 pushed by megha95
July 27, 2024 21:34 15s main
July 27, 2024 21:34 15s
July 26, 2024 23:35 19s
[Frontend] Add Usage data in each chunk for chat_serving. #6540 (#6652)
clang-format #4: Commit 58f5303 pushed by megha95
July 23, 2024 18:55 16s main
July 23, 2024 18:55 16s