AI/ML●●●Banger
We built an LLM inference engine in pure Python – no PyTorch, no Triton
30x faster cold start than vLLM with zero PyTorch dependencies.
WizardryBig BrainZero to One
zyoraclub
201mo ago
Back to browse
GitHub Repository
Pure C++23 LLM inference for Apple Silicon chips
20 starsC++
Gemma 3 inference in pure C++ with Metal acceleration
by ybubnov·Jul 4, 2026·2 points·1 comment
Similar Projects
AI/ML●●●Banger
GPT-2 inference in pure C#, 0 bytes allocated per token
GPT-2 inference in pure C# allocating zero bytes per token beats ONNX Runtime.
WizardryBig Brain
dev-on-bike
111mo ago
Developer Tools●Mid
Veil – A Minimal Neovim GUI for macOS with Metal Rendering
Metal rendering is nice, but Neovide already does GPU acceleration cross-platform.
CozyShip It
rainux
703mo ago
AI/ML●●●Banger
Alloy – a PyTorch backend and inference engine for Apple Silicon
Tile IR pipeline compiles Python kernels to Metal with automatic operator fusion for M1+.
WizardryBig BrainNiche Gem
rayanht
2013d ago
AI/ML●●●Banger
I wrote an LLM inference engine in pure Go – 48 tok/s zero dependencies
Pure Go LLM inference, zero dependencies, 48 tok/s—genuinely novel for Go ecosystem.
Zero to OneWizardryBig Brain
computerex
203mo ago
AI/ML●●●Banger
LLM inference slowdown fixed (177 experiments, +37% attention) – in 48h
Fused int4 attention kernel on Metal keeps LLM speed constant as context grows.
WizardrySolve My ProblemBig Brain
christinetyip
102mo ago