PR #25413 add webgpu support for GatherBlockQuantized

webgpu support for GatherBlockQuantized

guschmue committed 246 days ago

add 8bit quantization

guschmue committed 246 days ago

cleanup

guschmue committed 246 days ago

copilot feedback

guschmue committed 246 days ago

lintrunner

guschmue committed 246 days ago

move some code to 4bit case

guschmue committed 246 days ago

Merge branch 'main' into gs/GatherBlockQuantized

guschmue committed 245 days ago

fix issue with memory going out of scope

guschmue committed 245 days ago

onnxruntime add webgpu support for GatherBlockQuantized #25413 Merged