biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Speed up Punica compilation (#2632)

Browse Source
This commit is contained in:
Woosuk Kwon
2024-01-27 17:46:56 -08:00
committed by GitHub
parent 5f036d2bcc
commit f8ecb84c02
21 changed files with 100 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
csrc/punica/bgmv/bgmv_bf16_bf16_bf16.cu Normal file
View File

@@ -0,0 +1,4 @@
#include "bgmv_config.h"
#include "bgmv_impl.cuh"
FOR_BGMV_WIDE_NARROW(INST_BGMV_TWOSIDE, nv_bfloat16, nv_bfloat16, nv_bfloat16)