onnxruntime
902685f3 - Fix WebGPU GatherBlockQuantized FP8/FP4 dtype and broadcast-scale handling

Commit

9 days ago

Fix WebGPU GatherBlockQuantized FP8/FP4 dtype and broadcast-scale handling Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>

References

#32480 - Add FP8/FP4 block-quantized support to GatherBlockQuantized contrib op

Author

Copilot

Parents

1b927f27

onnxruntime 902685f3 - Fix WebGPU GatherBlockQuantized FP8/FP4 dtype and broadcast-scale handling

onnxruntime
902685f3 - Fix WebGPU GatherBlockQuantized FP8/FP4 dtype and broadcast-scale handling