Kaden-Schutt/hipfire
RDNA-native LLM inference engine in Rust. 59 tok/s Qwen3-8B on RX 5700 XT — 1.34x faster than llama.cpp. Custom 4-bit quantization, quantized KV cache, batched prefill. No Python, no link-time ROCm dependency.
14
/ 100
Experimental
No License
No Package
No Dependents
Maintenance
13 / 25
Adoption
0 / 25
Maturity
1 / 25
Community
0 / 25
Stars
—
Forks
—
Language
Rust
License
—
Category
Last pushed
Mar 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Kaden-Schutt/hipfire"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tracel-ai/burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on...
79
sonos/tract
Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
70
pykeio/ort
Fast ML inference & training for ONNX models in Rust
69
robertknight/rten
ONNX neural network inference engine
53
elixir-nx/ortex
ONNX Runtime bindings for Elixir
51