speculative-decoding skills

7 tagged speculative-decoding, measured the same way as everything else here.

Browse within: Draft Models 7Fast Inference 7Inference Optimization 7Latency Reduction 7Lookahead Decoding 7Parallel Generation 7Tree Attention 7emerging-techniques 7medusa 7

run-aeon-benchmark

01

AEON-7/Aeon-Bench-Pod

Skill Claude CodeCodex

Use when asked to run, benchmark, evaluate, or score an LLM with AEON Bench. You run the AEON Bench Pod on the user's machine, point it at a model, run the benchmark, and submit the signed result to the public leaderboard at aeon-bench.com. All work happens on the pod. The mothership only shows the board and accepts…

not rated 25 +2 19d ago A 83 tokens original MIT