2 Commits

Author	SHA1	Message	Date
fabolous005	708e152549	prain: int8/int4 experts quantized once on the GPU, rounds through vLLM's expert_map, [miss] min_weight skips experts not in VRAM; scripts: tune_moe, quality (answer NLL on identical token ids), bench --context, measure --quant	2026-10-28 22:07:25 +01:00
fabolous005	7bab776a16	prain: tiered forward with CPU path	2026-10-27 15:54:11 +01:00