~/ai-muninn
blog
github
中
~ / blog
/
tag / fp8
❯
grep -r "#fp8" ~/blog
2 matches
date
read
title
2026-04-07
10m
[Benchmark] From 19 to 50 tok/s: We Quantized Gemma 4 E4B to NVFP4 Before Anyone Else
#gemma-4
#e4b
#nvfp4
#fp8
2026-03-21
6m
[vLLM] FP8 KV Cache on GB10: Why Outputs Collapse into Repetition Loops
#vllm
#fp8
#kv-cache
#gb10
← back to all posts