llama.cpp
[SYCL] Fix WARP_SIZE=16 bug of Intel GPU
#8266
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
8
Changes
View On
GitHub
[SYCL] Fix WARP_SIZE=16 bug of Intel GPU
#8266
airMeng
merged 8 commits into
ggml-org:master
from
luoyu-intel:sycl-acc
github-actions
added
testing
github-actions
added
ggml
github-actions
added
SYCL
airMeng
requested a review
from
AidanBeltonS
1 year ago
luoyu-intel
force pushed
from
c9045c1c
to
3bf8c2c9
1 year ago
airMeng
approved these changes on 2024-07-03
NeoZhangJianyu
commented on 2024-07-03
NeoZhangJianyu
approved these changes on 2024-07-03
mofosyne
added
Review Complexity : Medium
fix group_norm ut
c675aaf0
split softmax
e50517b6
fix softmax
d70305b3
revert qx_k
0012f2c1
add concat support condition
870b607c
revert debug code
d7cf5f5a
move QK_WARP_SIZE to presets.hpp
ac8a4bd9
luoyu-intel
force pushed
from
4887fdce
to
ac8a4bd9
1 year ago
rebase work_space api
87098db6
airMeng
merged
a9554e20
into master
1 year ago
luoyu-intel
deleted the sycl-acc branch
1 year ago
Login to write a write a comment.
Login via GitHub
Reviewers
NeoZhangJianyu
airMeng
AidanBeltonS
Assignees
No one assigned
Labels
testing
Review Complexity : Medium
ggml
SYCL
Milestone
No milestone
Login to write a write a comment.
Login via GitHub