4 people dacaf5a400 Replace head_mapping params with num_kv_heads to attention kernel. (#1997) ...

Co-authored-by: wangguoya <wangguoya@baidu.com>
Co-authored-by: Yang Zhao <zhaoyangstar@foxmail.com>

2023-12-10 10:12:53 -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

Replace head_mapping params with num_kv_heads to attention kernel. (#1997)

2023-12-10 10:12:53 -08:00

attention_utils.cuh

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

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

dtype_bfloat16.cuh

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

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

dtype_float16.cuh

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

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

dtype_float32.cuh

[BugFix] Fix NaN errors in paged attention kernel (#936)

2023-09-04 09:20:06 +09:00