Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

OfinTech Desk
OfinTech Desk
It's a plan
It's a plan
Busbar
Busbar
Bifrost
Bifrost
Omnigraph
Omnigraph

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

#AI skills
Visit GitHub
Python
1.3k
116
2 contributors
MIT License
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Busbar

Control what AI can do before it acts

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Momentum

How fast sybil-solutions/inference-optimisation-skill is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Nov 16 – Nov 20, 2026

Stars +904 in 5 days

0200400600
493

Forks +116 in 5 days

050100
80

Merged PRs 0 in 5 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Top 25 in Python

13
Nov 16Nov 17Nov 18Nov 19Nov 20
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRsPython
Mon, Nov 16, 2026+0+00Not trending
Tue, Nov 17, 2026+493+800#13
Wed, Nov 18, 2026+192+190Not trending
Thu, Nov 19, 2026+151+150Not trending
Fri, Nov 20, 2026+68+20Not trending
Total+904+1160
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Mentions and achievements

Where people are talking about sybil-solutions/inference-optimisation-skill, and every badge it has earned
  1. Nov 202 posts
    • what do you think about this for the B70?

      Read full on X, posted by @f_merizalde

      @f_merizalde · x.com

    • This looks great but I'd want to make sure to do real work as the benchmarks for multiple reasons, and so want this to take part in a CI/CD instead of doing synthetic benchmark. Have you tried…

      Read full on X, posted by @BrianReborn_alt

      @BrianReborn_alt · x.com

  2. Nov 191 post
    • An agent skill for hill-climbing local LLM speed, not a list of flags. It computes the ceiling first, changes one thing at a time, and logs the failures too. On an Arc B390, 1-user decode went 43.6…

      Read full on X, posted by @kindlingdev

      @kindlingdev · x.com

  3. Nov 172 posts4 posts
    • the skill you published is genuinely close to magic. On the RTX 5060 TI 16GB and 2x DDR4 16GB 3200mhz. Thank you 🫶 The skill:

      Read full on X, posted by @DasaSantiago

      @DasaSantiago · x.com

    • Before tuning a local model, it helps to know how fast the hardware can go at all. We ran the calculator in a new open agent skill and got that ceiling in a second. It also showed that chat speed…

      Read full on X, posted by @AntonVlac

      @AntonVlac · x.com

    • 691 stars in a day: an agent skill that hill-climbs your local llm server's speed. compute the physics ceiling first, change one variable at a time, gate every result on a long-context stability…

      Read full on X, posted by @Z3nlyte

      @Z3nlyte · x.com

    • An agent skill that makes local LLMs run faster just went open source: 380 GitHub stars in 13 hours. You point Claude Code at your model server. It works out the top speed your hardware allows,…

      Read full on X, posted by @Yashpatil

      @Yashpatil · x.com

You might also like

Repositories close to sybil-solutions/inference-optimisation-skill
FeaturedAdvertise to 180K+ monthly visitors
OfinTech Desk

An open-source AI workspace for finance and accounting teams, in which every figure is traced to its source

Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

It's a plan

Open-source Linear alternative

An issue tracker where AI agents take the work you assign them

Busbar

Control what AI can do before it acts

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

bigattichouse/llama-optimize

Python

Automating llama.cpp LLM parameter optimization for highest speed/best fit using Morris/Taguchi DoE sweeps.

964

bentoml/llm-optimizer

Python

Benchmark and optimize LLM inference across frameworks with ease

20526

KittenML/inferencekit

Python

Turn your coding agent into an inference engineer. Make your models faster across any hardware.

332

Tensward/tensward

Python

Profile and diagnose LLM serving on your own GPU. Measures your vLLM setup on your real workload and suggests what to change.

221

rednote-machine-learning/Inference-autopilot

Python

Evidence-driven SGLang inference deployment optimization.

1431

gengchaogit/llm_speedtest

HTML

Local LLM Inference Speed Test Tool

25620

Andyyyy64/whichllm

Python

Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.

6.8k405

huggingface/optimum-benchmark

Python

🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.

34168

RahulSChand/gpu_poor

JavaScript

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

1.4k83