DeepSpeed
47% FastGen speedup for low workload - refactor allocator
#5090
Merged

47% FastGen speedup for low workload - refactor allocator #5090

HeyangQin
HeyangQin Refactor Allocator class and add caching for empty_from method
1cd9adcb
HeyangQin fix format
2cfdbe00
HeyangQin HeyangQin marked this pull request as ready for review 1 year ago
HeyangQin HeyangQin requested a review from mrwyattii mrwyattii 1 year ago
HeyangQin HeyangQin requested a review from awan-10 awan-10 1 year ago
HeyangQin HeyangQin requested a review from arashb arashb 1 year ago
tjruwase Merge branch 'master' into HeyangQin/fastgen_allocator_optim
e1fd2c4a
mrwyattii
mrwyattii approved these changes on 2024-02-08
HeyangQin HeyangQin changed the title Refactor FastGen allocator and add caching for empty_from method 47% FastGen speedup for low workload - Refactor allocator 1 year ago
HeyangQin HeyangQin changed the title 47% FastGen speedup for low workload - Refactor allocator 47% FastGen speedup for low workload - refactor allocator 1 year ago
HeyangQin HeyangQin merged 3c811c96 into master 1 year ago
mrwyattii mrwyattii deleted the HeyangQin/fastgen_allocator_optim branch 1 year ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone