vllm/csrc/attention at main - vllm - Gitea: Git with a cup of tea

obscura/vllm

Fork 0

mirror of https://github.com/vllm-project/vllm.git synced 2026-08-13 01:08:14 +00:00

Files

T

History

22a58640b4 [9/n] Migrate attention and cache kernels to torch stable ABI (continued) (#43717 )

Signed-off-by: Chris Leonard <[email protected]>
Signed-off-by: Mikayla Gawarecki <[email protected]>
Co-authored-by: Mikayla Gawarecki <[email protected]>
Co-authored-by: Shengqi Chen <[email protected]>

2026-05-29 04:44:45 +00:00

attention_dtypes.h

Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290 )

2024-04-03 14:15:55 -07:00

attention_generic.cuh

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722 )

2024-05-22 07:18:41 +00:00

dtype_bfloat16.cuh

[CI/Build] Suppress divide-by-zero and missing return statement warnings (#7001 )

2024-08-05 16:00:01 -04:00

dtype_float16.cuh

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722 )

2024-05-22 07:18:41 +00:00

dtype_float32.cuh

[CI/Build] Enforce style for C++ and CUDA code with clang-format (#4722 )

2024-05-22 07:18:41 +00:00

dtype_fp8.cuh

[6/n] Migrate activation kernels, gptq, gguf, non cutlass w8a8 to libtorch stable ABI (continued) (#42663 )

2026-05-20 00:18:12 -07:00