Hill-climb the serving speed of a local LLM on any hardware (NVIDIA, AMD, Intel, Apple, unified-memory laptops, multi-GPU) and any quantization (GGUF, EXL2/EXL3, AWQ/GPTQ, FP8, MLX, BF16): single-user and concurrent decode tok/s, speculative decoding, prefill tok/s, KV cache size, startup time and TTFT, under a memory cap and with full-context stability. Computes the theoretical ceiling first, runs noise-controlled A/B experiments, keeps a ledger, and qualifies the winner before publishing it. Use when asked to optimise, tune, speed up, benchmark or hill-climb a model server (vLLM, SGLang, llama.cpp, ExLlama/TabbyAPI, MLX, TensorRT-LLM...), to find the maximum possible tok/s on a machine, or to publish a tuned recipe. Triggers: hill climb, tok/s, decode speed, prefill speed, MTP, EAGLE, draft model, speculative decoding, KV cache, TTFT, startup time, theoretical maximum.
Sybil Solutions
A place for all things AI
1 skill 1.4k United States of America Synced
Skills
sybil-solutions/inference-optimisation-skill
Agent skill for hill-climbing local LLM serving speed (decode, speculative decoding, prefill, KV, startup, TTFT) on any hardware and quantization
1 skill 1.4k
npx skilld add sybil-solutions/inference-optimisation-skill --allSkills published by Sybil Solutions. Checked GitHub just now