Skip to content
#

ampere

Here are 28 public repositories matching this topic...

First public benchmark of llama.cpp speculative decoding on Qwen3.6-35B-A3B with a single RTX 3090 (post PR #19493 merge, 2026-04-19). 19 configurations covering ngram-cache, ngram-mod, and classic draft with vocab-matched Qwen3.5-0.8B. Finding: no variant achieves net speedup on Ampere + A3B MoE. Raw JSON, plots, full reproducibility.

  • Updated Apr 21, 2026
  • Python

Improve this page

Add a description, image, and links to the ampere topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the ampere topic, visit your repo's landing page and select "manage topics."

Learn more