Daniel Hiltgen 4fb47ed368 MXFP4 support ...

This implements the Open Compute Microscaling (MX) FP4 format
as a tensor type with backend implementations focusing
on mulmat and mulmatid on CPU, CUDA, and Metal.

2025-08-04 11:01:37 -07:00

..

ggml

MXFP4 support

2025-08-04 11:01:37 -07:00

gguf

Reapply "feat: incremental gguf parser (#10822)" (#11114) (#11119)

2025-06-20 11:11:40 -07:00

util/bufioutil

next ollama runner (#7913)

2025-02-13 16:31:21 -08:00

config.go

add new gemma model (#11204)

2025-06-25 21:47:09 -07:00