llama.cpp
[SYCL] Optimize mul_mat for Q4_0 on Intel GPU
#12035
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
10
Changes
View On
GitHub
[SYCL] Optimize mul_mat for Q4_0 on Intel GPU
#12035
NeoZhangJianyu
merged 10 commits into
ggml-org:master
from
NeoZhangJianyu:opt_reorder
opt performance by reorder for Intel GPU
78e232a0
detect hw type and save opt feature, and print opt feature
7a6b48d7
correct name
63e5285d
support optimize graph once when compute graph, record the opt status…
5cfde909
add env variable GGML_SYCL_DISABLE_OPT for debug
4eaab12e
github-actions
added
examples
github-actions
added
ggml
github-actions
added
SYCL
NeoZhangJianyu
requested a review
from
airMeng
298 days ago
airMeng
commented on 2025-02-24
use syclex::architecture replace the custom hw define, update the gui…
0e91e0eb
add performance data
b3570b92
mv getrows functions to separeted files
f1117218
github-actions
added
documentation
airMeng
approved these changes on 2025-02-24
Merge branch 'master' into opt_reorder
c541d6ae
fix global variables
30ddc909
NeoZhangJianyu
merged
08d59862
into master
297 days ago
Alcpz
commented on 2025-02-24
Login to write a write a comment.
Login via GitHub
Reviewers
airMeng
ky438
Alcpz
Assignees
No one assigned
Labels
documentation
examples
ggml
SYCL
Milestone
No milestone
Login to write a write a comment.
Login via GitHub