vllm/bgmv at 54814fd85b5182fc140febfebbb2560420d2ed2a - vllm - 丝路新云-代码仓

xinyun/vllm

mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-21 02:07:03 +08:00

History

Tyler Michael Smith 5d2a1a9cf0

Unmark more files as executable (#5962 )

2024-06-28 17:34:56 -04:00

..

bgmv_bf16_bf16_bf16.cu

[Kernel] Full Tensor Parallelism for LoRA Layers (#3524 )

2024-04-27 00:03:48 -07:00

bgmv_bf16_fp32_bf16.cu

[Kernel] Full Tensor Parallelism for LoRA Layers (#3524 )

2024-04-27 00:03:48 -07:00

bgmv_config.h

Unmark more files as executable (#5962 )

2024-06-28 17:34:56 -04:00

bgmv_fp16_fp16_fp16.cu

[Kernel] Full Tensor Parallelism for LoRA Layers (#3524 )

2024-04-27 00:03:48 -07:00

bgmv_fp16_fp32_fp16.cu

[Kernel] Full Tensor Parallelism for LoRA Layers (#3524 )

2024-04-27 00:03:48 -07:00

bgmv_fp32_bf16_bf16.cu

[Kernel] Full Tensor Parallelism for LoRA Layers (#3524 )

2024-04-27 00:03:48 -07:00

bgmv_fp32_fp16_fp16.cu

[Kernel] Full Tensor Parallelism for LoRA Layers (#3524 )

2024-04-27 00:03:48 -07:00

bgmv_impl.cuh

[ROCm] Add support for Punica kernels on AMD GPUs (#3140 )

2024-05-09 09:19:50 -07:00

generator.py

[Kernel] Full Tensor Parallelism for LoRA Layers (#3524 )

2024-04-27 00:03:48 -07:00

vec_dtypes.cuh

[ROCm] Add support for Punica kernels on AMD GPUs (#3140 )

2024-05-09 09:19:50 -07:00