Add CudaQuantizer to onnxruntime.quantization #29509
tianleiwu
changed the title Add MoeCudaQuantizer to onnxruntime.quantization Add CudaQuantizer to onnxruntime.quantization 8 days ago
Add MoeCudaQuantizer
4a8694c4
add qmoe block quantization
2414fa48
tianleiwu
force pushed
from
439fc781
to
2414fa48
8 days ago
Add full_range support for block quantization
db21ced1
address feedbacks
d6953441
fix(quantization): resolve CodeQL uninitialized-variable warnings
9540920e
add qmoe_ prefix to some functions
87d1341f
Update onnxruntime/test/python/transformers/test_moe_cuda.py
de6e6ed9
tianleiwu
enabled auto-merge (squash) 8 days ago
tianleiwu
merged
1990bd5f
into main 7 days ago
tianleiwu
deleted the tlwu/qmoe_quantizer branch 7 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub