SkillPedia Skills Encyclopedia
中文 EN

inference-optimisation-skillsybil-solutions/inference-optimisation-skill

[Core Features]: A skill for hill-climbing local LLM server speed on any hardware and quantization,…

No ratings yet Rate this skill
Stars1.2k
Forks110
Watchers—
Open Issues—

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/sybil-solutions/inference-optimisation-skill.git

OverviewOverview

[Core Features]: A skill for hill-climbing local LLM server speed on any hardware and quantization, covering single-user and concurrent decode, speculative decoding, prefill, KV cache size, startup time and time to first token under a memory cap with full-context stability checks. The workflow computes a theoretical ceiling, changes one thing at a time, measures against interleaved controls, logs every result including failures and pins a clean build before publishing, with measured speedups on Intel Arc iGPU among the examples. [Applicable Scenarios]: Inference tuning, KV cache sizing, speculative decoding and benchmark measurement. [Target Roles]: Inference engineer, performance engineer and AI infrastructure team.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID5994
Data sourceGitHub
Repositorysybil-solutions/inference-optimisation-skill
CategoryData & Infrastructure Skills / Local LLM Inference Tuning Skill
Primary languageNot specified
LicenseNot specified
Default branch
GitHub repository ID
Rank#760 (position within the source ranking)
Site-wide popularity rank#871 (computed live from Stars, across all 5897 entries)

GrowthStar / Fork growth

Still collecting First record taken on 2026-11-20. Two days of data are needed before a trend line can be drawn.

TimelineTimeline

Repository created2026-11-20 20:55:164 hours ago
Data last updated2026-11-20 20:55:164 hours ago
Last commit—

CommitLatest commit

New Feature: inference-optimisation skill: hardware- and quant-agnostic LLM serving hill-climb SKILL.md procedure (ceilings first, interleaved controls, full-context gates, publishing), references (ceilings, methodology, levers with measured evidence, gotchas, publishing), engine-agnostic harness (bench.py, cei

fda968e v5.5 0xSero 2026-11-16

Next stepsNext steps