vllm/csrc/quantization/fp8 at 8a74c68bd1ae48cb71e4c3bf9d7ff9a2ef8f9dae - vllm - Gitea: Git with a cup of tea

wassname/vllm

mirror of https://github.com/wassname/vllm.git synced 2026-08-19 12:40:48 +08:00

Files

T

History

Varun Sundar RabindranathandVarun Sundar Rabindranath b5241e41d9 [ Kernel ] FP8 Dynamic-Per-Token Quant Kernel (#6511 )

Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

2024-07-18 01:38:35 +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

common.cu

[ Kernel ] FP8 Dynamic-Per-Token Quant Kernel (#6511 )

2024-07-18 01:38:35 +00:00

fp8_marlin.cu

[Kernel] Expand FP8 support to Ampere GPUs using FP8 Marlin (#5975 )

2024-07-03 17:38:00 +00:00