biondizzle 4d67b570b9 fix: descriptive tqdm labels — uint8→NVFP4 and NVFP4→FP8/BF16 ...

Makes it crystal clear what's happening:
- Experts: direct uint8→float4 view-cast (Blackwell native, no BF16)
- Convert: NVFP4→FP8/BF16 for attention weights (non-expert path)

2026-05-16 04:28:25 +00:00

..

patches

fix: descriptive tqdm labels — uint8→NVFP4 and NVFP4→FP8/BF16

2026-05-16 04:28:25 +00:00

nvfp4_cutedsl.py

fix: L1 gate/up split — intermediate_size is per-projection, not fused

2026-05-16 04:04:40 +00:00