aisim

AISim predicts LLM serving behavior and searches for strong deployment configurations offline, without bringing up a GPU serving cluster

ai-dynamo/aisim

View on GitHub ↗

AISim predicts LLM serving behavior and searches for strong deployment configurations offline, without bringing up a GPU serving cluster

aisim grew +40.4% in the last 30 days, ranks 243rd of 343 in Inference Optimization, actively maintained, last commit today.

Star trajectory

36 days tracked
2026-10-17139 stars today2026-11-22
Momentum

+40.4% in 30d, above the Inference Optimization median of +1.6%.

Maintenance

Last commit today, fresher than the median of 16d.

How it compares in Inference Optimization

aisim
139
stars
+40.4% 30d
commit today
Inference Optimization median
242
stars
+1.6% 30d
commit ~16d ago
Leader · supertonic
13.8k
stars
-0.1% 30d
commit 74 days ago

Ranked 243rd of 343 by stars.

Ranked by shared tags, then keywords, then stars
  1. LLM Benchmark for Throughput via Ollama (Local LLMs)

    +2 (+0.5%) in 30d · Committed 25d ago · Python · MIT

    Shares Inference Optimization

  2. Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU…

    +28 (+13%) in 30d · Committed 5d ago · Python · MIT

    Shares Inference Optimization

  3. Optimized GPU compiler for LLM inference. Choose from a list of optimized recipes or optimize your own model…

    +12 (+10%) in 30d · Committed today · Python · Apache-2.0

    Shares Inference Optimization

  4. llm theoretical performance analysis tools and support params, flops, memory and latency analysis.

    +1 (+0.8%) in 30d · Committed 498d ago · Python

    Shares Inference Optimization

  5. Run a 110B on a 2016 PC with 16 GB RAM. Know your tok/s before you download. Placement beats budget: predicts…

    +3 (+3.3%) in 30d · Committed 46d ago · Python · MIT

    Shares Inference Optimization

  6. An open-source virtual AI Infra team that discovers, benchmarks, and safely upgrades local LLM inference—with…

    -1 (-1.2%) in 30d · Committed 74d ago · Python · Apache-2.0

    Shares Inference Optimization

  7. Local decision engine with typed, calibrated outputs (Noul/Choice/Score): cheap→strong cascade, ECE/Brier…

    Committed yesterday · Python · Apache-2.0

    Shares Inference Optimization

  8. Stop renting your AI. Throttle tests your AI calls against cheaper models on your own traffic and moves the…

    +0 (+0.0%) in 30d · Committed yesterday · Python · MIT

    Shares Inference Optimization

  9. Will this LLM run on this Mac, and how fast. Memory and tokens per second for any model on any Apple Silicon…

    +0 in 30d · Committed 62d ago · Python · MIT

    Shares Inference Optimization

  10. Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

    -15 (-0.1%) in 30d · Committed 74d ago · Swift · MIT

    Shares Inference Optimization

Language
Python
License
Other
Contributors
72
Forks
67
Watchers
0
Open issues
37
Releases
3
Created
2026-08-11
Stars this week
+5

You've seen where aisim stands today.

Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain aisim?

Claim this page to add your own call-to-action.

Claim this page