[Kernel] Adding bias epilogue support for cutlass_scaled_mm (#5560)

Co-authored-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
This commit is contained in:
Luka Govedič
2024-06-26 15:16:00 +00:00
committed by GitHub
co-authored by Chih-Chieh-Yang Lucas Wilkinson
parent 6984c02a27
commit 5bfd1bbc98
8 changed files with 385 additions and 136 deletions
+2 -1
View File
@@ -2,7 +2,8 @@ cmake_minimum_required(VERSION 3.21)
project(vllm_extensions LANGUAGES CXX)
option(VLLM_TARGET_DEVICE "Target device backend for vLLM" "cuda")
# CUDA by default, can be overridden by using -DVLLM_TARGET_DEVICE=... (used by setup.py)
set(VLLM_TARGET_DEVICE "cuda" CACHE STRING "Target device backend for vLLM")
message(STATUS "Build type: ${CMAKE_BUILD_TYPE}")
message(STATUS "Target device: ${VLLM_TARGET_DEVICE}")