[ARK] Optimize SYCL-TLA woqgemm_s8 on B70 #2133
inference pass v0.1
ebf4a789
inference pass v1.0
9f7bbca2
Zhenzhong1
changed the title [ARK] Optimize SYCL-TLA woqgemm_s8 [ARK] Optimize SYCL-TLA woqgemm_s8 on B60&B70 6 days ago
Zhenzhong1
changed the title [ARK] Optimize SYCL-TLA woqgemm_s8 on B60&B70 [ARK] Optimize SYCL-TLA woqgemm_s8 on B70 5 days ago
remove useless code
9cc773be
chensuyue
added this to the 0.15.0 milestone 5 days ago
Zhenzhong1
marked this pull request as ready for review 5 days ago
Merge branch 'main' into zhenzhong/woqgemm_s8_update
5b300a0f
fixed ark_auto_s8_bug
5651c63d
fixed ark_auto_s8_bug scale fp32 and auto_s8=-1 by default
d7034238
fixed test_xpu w8a8 bug
f6fa1651
Merge branch 'main' into zhenzhong/woqgemm_s8_update
2a3d4a0f
fixed copilot issues
c52cc3d4
[pre-commit.ci] auto fixes from pre-commit.com hooks
8e3d2919
fixed copilot issues
32be4740
Merge branch 'main' into zhenzhong/woqgemm_s8_update
dac6b1f0
- Remove the old B70 oneAPI < 2026 runtime fallback
d1d5c5db
a32543254
approved these changes
on 2026-08-14
chensuyue
merged
2ea60e55
into main 2 days ago
chensuyue
deleted the zhenzhong/woqgemm_s8_update branch 2 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub