xla
Calculate vmem limit dynamically in the quantized matmul kernel.
#9470
Merged

Calculate vmem limit dynamically in the quantized matmul kernel. #9470

vanbasten23
vanbasten23 Set vmem_limit according to block sizes.
f30367ad
vanbasten23 linter
66d6100d
vanbasten23 vanbasten23 requested a review from yaochengji yaochengji 1 year ago
vanbasten23 vanbasten23 marked this pull request as ready for review 1 year ago
yaochengji
yaochengji approved these changes on 2025-07-10
yaochengji
yaochengji commented on 2025-07-10
vanbasten23 make vmem_limit account for vreg spill etc.
2abb8568
vanbasten23
vanbasten23 vanbasten23 merged 83dc9da8 into master 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone