Files
nvfp4-megamoe-kernel/vllm
biondizzle af6583eb19 fix: unpack uint8 NVFP4→bf16 for non-stacked params (weights_proj)
indexer.weights_proj is uint8 [64,3584] in checkpoint but bf16 [64,7168]
in model. The uint8→bf16 unpack logic only ran in the stacked_params
loop, so non-stacked NVFP4 params hit a size mismatch assertion.
2026-05-15 00:51:50 +00:00
..