QMoE CPU Performance Update (Up to 4x on 4-bit) #27364
Fix QMoE CPU
ed0478ad
prepack and cache to improve QMoE perf
2c838293
move cache to prepack; allow q4gemm for block_size=32
2b256017
Turn on q4 gemm by default if there is no accuracy loss
e9dcd411
refine tests
dec88677
refactor CheckInputs
4af13153
fix build
23cdf2d9
robust shape storage
6d351fed
Merge remote-tracking branch 'origin/main' into tlwu/20260216/qmoe_cp…
100738b8
refactoring
0b4c783a
review feedback
abef62be
address AI feedback
11d30ce0
tianleiwu
enabled auto-merge (squash) 166 days ago
tianleiwu
merged
b2a6e69e
into main 165 days ago
tianleiwu
deleted the tlwu/20260216/qmoe_cpu_q4_perf branch 165 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub