vllm/csrc/attention at 6ccc0bfffbcf1b7e927cc3dcf4159fc74ff94d40 - vllm

wassname/vllm

Fork 0

mirror of https://github.com/wassname/vllm.git synced 2026-07-23 13:10:20 +08:00

Files

T

History

6ccc0bfffb Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836 )

Co-authored-by: Philipp Moritz <pcmoritz@gmail.com>
Co-authored-by: Amir Balwel <amoooori04@gmail.com>
Co-authored-by: root <kuanfu.liu@akirakan.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
Co-authored-by: kuanfu <kuanfu.liu@embeddedllm.com>
Co-authored-by: miloice <17350011+kliuae@users.noreply.github.com>

2023-12-07 23:16:52 -08:00

attention_dtypes.h

Improve setup script & Add a guard for bfloat16 kernels (#130 )

2023-05-27 00:59:32 -07:00

attention_generic.cuh

Change the name to vLLM (#150 )

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

attention_kernels.cu

Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836 )

2023-12-07 23:16:52 -08:00

attention_utils.cuh

Merge EmbeddedLLM/vllm-rocm into vLLM main (#1836 )