llama.cpp
fc3f10b3 - sycl: fix UE4M3 parsing (#25608)

Commit
47 days ago
sycl: fix UE4M3 parsing (#25608) The NVFP4 quantization format stores a scaling factor for every group of 16 weights, packed into a single UE4M3 byte. The SYCL GPU code was converting these scale values using the E4M3 path, but that's *signed*, and these are unsigned values.
Author
Parents
Loading