~/ai-muninn
search
⌘K
blog
github
中
~ / blog
/
tag / qwen3.5
❯
grep -r "#qwen3.5" ~/blog
2 matches
date
read
title
2026-06-11
15m
[Benchmark] Qwen3.5-122B on DGX Spark: the 17 tok/s GDN wall was real — but the 2× fix was outside vLLM
#qwen3.5
#dgx-spark
#gb10
#gdn
2026-03-30
8m
[Benchmark] TurboQuant on GX10: Is 3-bit KV Cache Compression Actually Lossless?
#turboquant
#kv-cache
#quantization
#vllm
← back to all posts