vllm/csrc/quantization at a36de682d4283c60777bc3022ed3ce71cd90b904 - vllm - Gitea: Git with a cup of tea

wassname/vllm

mirror of https://github.com/wassname/vllm.git synced 2026-08-11 11:28:04 +08:00

Files

T

History

Tyler Michael SmithandGitHub 8674f9880e [Kernel] Fixup for CUTLASS kernels in CUDA graphs (#4954 )

Pass the CUDA stream into the CUTLASS GEMMs, to avoid future issues with CUDA graphs

2024-05-22 14:10:43 +00:00

..

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

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

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

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

[Kernel] Fixup for CUTLASS kernels in CUDA graphs (#4954 )

2024-05-22 14:10:43 +00:00

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

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

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

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

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

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

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

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

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

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