auto-tuning
neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
- 2.7k
- Python
- Apache-2.0
- 2 d ago
awesome-machine-learning-in-compilers
Must read research papers and links to tools and datasets that are related to using machine learning for compilers and systems optimisation
- 1.7k
- CC0-1.0
- 3 mo ago
kernel-ml
Machine Learning Framework for Operating Systems - Brings ML to Linux kernel
- 261
- C
- Apache-2.0
- 5 y ago
VibeCodeHPC
CLI-based multi-agents for Auto-Tuning (e.g. HPC code optimazation loops) supporting Local LLMs
- 43
- Python
- MIT
- 6 wk ago
ck-crowdtuning
Collective Knowledge crowd-tuning extension to let users crowdsource their experiments (using portable Collective Knowledge workflows) such as performance benchmarking, auto tuning and machine learning across diverse platforms with Linux, Windows, MacOS and Android provided by volunteers. Demo of DNN crowd-benchmarking and crowd-tuning:
- 36
- Python
- BSD-3-Clause
- 5 y ago
noeticos
NoeticOS: the JIT compiler for agents. Adaptive runtime intelligence for production agents, per-task-class tuning of model, temperature, topP, maxTurns, retryBudget, and contextShare with confidence-bound bandits, deterministic canary rollouts, automatic rollback, and a complete decision audit log. Zero dependencies, TypeScript, edge-ready.
- 1
- TypeScript
- Apache-2.0
- 2 mo ago
vllm_auto_tune
Automated vLLM server parameter tuning tool. Finds optimal max-num-seqs and max-num-batched-tokens to maximize throughput. Includes presets for Llama/Qwen/Mixtral, batch processing, result analysis with visualizations, and environment checks. Supports TPU/GPU with latency constraints.
- 3
- Shell
- 13 mo ago
backoff
:bowtie: Backoff uses an exponential backoff algorithm to backoff between retries with optional auto-tuning functionality.
- 13
- Go
- MIT
- 9 y ago





