vllm/layers at 203d4f82ac137f04c0e487bbdbba86b3cf3ae7bf - vllm - 丝路新云-代码仓

xinyun/vllm

mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-02 04:07:27 +08:00

History

Roy f510395bbf

[BugFix][Frontend] Fix completion logprobs=0 error (#3731 )

2024-03-29 09:38:21 -07:00

..

[Kernel] Add MoE Triton kernel configs for A100 40GB (#3700 )

2024-03-28 15:26:24 -07:00

[CI] Try introducing isort. (#3495 )

2024-03-25 07:59:47 -07:00

[CI] Try introducing isort. (#3495 )

2024-03-25 07:59:47 -07:00

__init__.py

Change the name to vLLM (#150 )

2023-06-17 03:07:40 -07:00

activation.py

[1/n][Chunked Prefill] Refactor input query shapes (#3236 )

2024-03-20 14:46:05 -07:00

layernorm.py

Revert "Refactor llama family models (#2637 )" (#2851 )

2024-02-13 09:24:59 -08:00

linear.py

[CI] Try introducing isort. (#3495 )

2024-03-25 07:59:47 -07:00

logits_processor.py

[Hardware][Neuron] Refactor neuron support (#3471 )

2024-03-22 01:22:17 +00:00

rejection_sampler.py

[CI] Try introducing isort. (#3495 )

2024-03-25 07:59:47 -07:00

rotary_embedding.py

[BugFix] tensor.get_device() -> tensor.device (#3604 )

2024-03-24 19:01:13 -07:00

sampler.py

[BugFix][Frontend] Fix completion logprobs=0 error (#3731 )

2024-03-29 09:38:21 -07:00

vocab_parallel_embedding.py

[CI] Try introducing isort. (#3495 )

2024-03-25 07:59:47 -07:00