Files
llama.cpp/ggml
Chris LeeandGitHub fc3f10b389 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.
2026-08-07 08:28:53 +03:00
..
2026-08-07 08:28:53 +03:00