EAGLE-3

Mentions · 7d0
Mentions · 30d0
All mentions1
First seenSep 7, 2026
Last mentionedSep 7, 2026

Timeline

1 articles · newest first

Speculative Decoding in vLLM on AMD GPUs

vLLM benchmarks speculative decoding on AMD Instinct MI300X and MI355X GPUs across five drafting methods including EAGLE-3 and native MTP.

Hacker News · AISep 7, 09:26 UTC · Sep 7, 2026AI tools & infra HN 141 points · 52 comments10 · 4 reads

Appears with

ROCmproduct · 1
AMDvendor · 1
AMDorganization · 1
vLLMproduct · 1

Entities are extracted by the model from each article. First seen Sep 7, 2026, last mentioned Sep 7, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.