Skip to content

Actions: bigPYJ1151/vllm

clang-format

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
58 workflow runs
58 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[Bugfix] Fix lora loading for Compressed Tensors in #9120 (#9179)
clang-format #33: Commit 21906a6 pushed by bigPYJ1151
October 9, 2024 12:19 17s main
October 9, 2024 12:19 17s
support bitsandbytes quantization with more models (#9148)
clang-format #32: Commit 2f4117c pushed by bigPYJ1151
October 9, 2024 02:03 19s main
October 9, 2024 02:03 19s
[Core] Refactor GGUF parameters packing and forwarding (#8859)
clang-format #31: Commit f19da64 pushed by bigPYJ1151
October 7, 2024 11:55 14s main
October 7, 2024 11:55 14s
[Misc] Remove vLLM patch of BaichuanTokenizer (#8921)
clang-format #30: Commit b0298aa pushed by bigPYJ1151
September 28, 2024 12:35 21s main
September 28, 2024 12:35 21s
[Bugfix] Fix potentially unsafe custom allreduce synchronization (#8558)
clang-format #29: Commit cc4325b pushed by bigPYJ1151
September 24, 2024 08:58 14s main
September 24, 2024 08:58 14s
[torch.compile] hide slicing under custom op for inductor (#8384)
clang-format #28: Commit 7de49aa pushed by bigPYJ1151
September 12, 2024 09:08 18s main
September 12, 2024 09:08 18s
[Frontend] Create ErrorResponse instead of raising exceptions in run_…
clang-format #27: Commit cea95df pushed by bigPYJ1151
September 11, 2024 06:04 25s main
September 11, 2024 06:04 25s
[BugFix] Fix Granite model configuration (#8216)
clang-format #26: Commit baa5467 pushed by bigPYJ1151
September 6, 2024 04:58 14s main
September 6, 2024 04:58 14s
[Core] Support load and unload LoRA in api server (#6566)
clang-format #25: Commit db3bf7c pushed by bigPYJ1151
September 6, 2024 02:33 18s main
September 6, 2024 02:33 18s
[Frontend] Multimodal support in offline chat (#8098)
clang-format #24: Commit 855c262 pushed by bigPYJ1151
September 4, 2024 05:32 14s main
September 4, 2024 05:32 14s
[TPU] Align worker index with node boundary (#7932)
clang-format #23: Commit e2b2aa5 pushed by bigPYJ1151
September 2, 2024 06:48 21s main
September 2, 2024 06:48 21s
[Bugfix]: Use float32 for base64 embedding (#7855)
clang-format #22: Commit 0b76999 pushed by bigPYJ1151
August 26, 2024 05:17 20s main
August 26, 2024 05:17 20s
[core][misc] update libcudart finding (#7620)
clang-format #21: Commit d95cc0a pushed by bigPYJ1151
August 17, 2024 14:09 16s main
August 17, 2024 14:09 16s
[Bugfix][TPU] Correct env variable for XLA cache path (#7544)
clang-format #20: Commit fc93e56 pushed by bigPYJ1151
August 15, 2024 08:06 16s main
August 15, 2024 08:06 16s
Fix empty output when temp is too low (#2937)
clang-format #19: Commit c134a46 pushed by bigPYJ1151
August 14, 2024 06:25 15s main
August 14, 2024 06:25 15s
[LoRA] Relax LoRA condition (#7146)
clang-format #18: Commit 9118217 pushed by bigPYJ1151
August 6, 2024 04:53 15s main
August 6, 2024 04:53 15s
[Model] Add multi-image support for minicpmv (#7122)
clang-format #17: Commit 7b86e7c pushed by bigPYJ1151
August 5, 2024 03:30 18s main
August 5, 2024 03:30 18s
[Misc] Pass cutlass_fp8_supported correctly in fbgemm_fp8 (#6871)
clang-format #16: Commit 3eeb148 pushed by bigPYJ1151
July 29, 2024 06:31 16s main
July 29, 2024 06:31 16s
Fix ReplicatedLinear weight loading (#6793)
clang-format #15: Commit 062a1d0 pushed by bigPYJ1151
July 26, 2024 03:35 16s main
July 26, 2024 03:35 16s
July 25, 2024 12:20 17s
[CI/Build] vLLM cache directory for images (#6444)
clang-format #13: Commit d970115 pushed by bigPYJ1151
July 16, 2024 09:59 17s main
July 16, 2024 09:59 17s
[ Misc ] Remove separate bias add (#6353)
clang-format #12: Commit 6047187 pushed by bigPYJ1151
July 12, 2024 07:18 15s main
July 12, 2024 07:18 15s
July 5, 2024 01:14 19s
[Distributed][Core] Support Py39 and Py38 for PP (#6120)
clang-format #10: Commit 0ed646b pushed by bigPYJ1151
July 4, 2024 01:51 16s main
July 4, 2024 01:51 16s
[Bugfix] Fix compute_logits in Jamba (#6093)
clang-format #9: Commit 7cd2ebb pushed by bigPYJ1151
July 3, 2024 13:22 22s main
July 3, 2024 13:22 22s