nf3-kernel

Tag

Cards List
#nf3-kernel

@0xSero: We found a way to run GLM-5.2 with full context in vLLM without pruning. - top 32 experts NVFP4 - rest fp3 - intel auto…

X AI KOLs Following · 22h ago Cached

A community researcher enabled running GLM-5.2 (753B parameters, all 256 experts) in vLLM without pruning via a hybrid quantization (NVFP4, NF3, MXFP8), fitting on 4×96GB GPUs with ~307k KV cache and near-FP8 accuracy.

0 favorites 0 likes
← Back to home

Submit Feedback