onnxruntime
Add MatMul 4bits support on GPU
#17890
Merged

Add MatMul 4bits support on GPU #17890

yufenglee merged 1 commit into main from yufeng/matmul_int4_gpu
yufenglee
yufenglee yufenglee requested a review from chenfucn chenfucn 2 years ago
yufenglee yufenglee requested a review from zhanghuanrong zhanghuanrong 2 years ago
yufenglee yufenglee requested a review from edgchen1 edgchen1 2 years ago
yufenglee yufenglee requested a review from tianleiwu tianleiwu 2 years ago
yufenglee yufenglee force pushed from df1b455c to 2a5be5e6 2 years ago
yufenglee yufenglee force pushed from 2a5be5e6 to 4131d145 2 years ago
yufenglee Add MatMul 4bits support on GPU
8badbcc2
yufenglee yufenglee force pushed from 4131d145 to 8badbcc2 2 years ago
jywu-msft jywu-msft requested a review from adrianlizarraga adrianlizarraga 2 years ago
tianleiwu
tianleiwu commented on 2023-10-12
zhanghuanrong
zhanghuanrong commented on 2023-10-13
zhanghuanrong
zhanghuanrong approved these changes on 2023-10-13
tianleiwu
tianleiwu approved these changes on 2023-10-13
tianleiwu
tianleiwu commented on 2023-10-13
tianleiwu
tianleiwu commented on 2023-10-13
tianleiwu
tianleiwu commented on 2023-10-13
yufenglee yufenglee merged 11af3444 into main 2 years ago
yufenglee yufenglee deleted the yufeng/matmul_int4_gpu branch 2 years ago
yufenglee yufenglee added release:1.16.2
faxu faxu added triage:approved
faxu faxu added sdxl_llama
tianleiwu tianleiwu removed triage:approved
tianleiwu tianleiwu removed release:1.16.2
tianleiwu tianleiwu removed sdxl_llama

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone