AI/ML●●●Banger
EdgeRunner – run GGUF models with Swift and Metal
Pure Swift inference engine beats llama.cpp without any C++ bindings.
WizardryZero to One
karc14
2016d ago
Back to browse
Ext-Infer – Native LLM Inference and Embeddings for PHP
by eamann·Jun 7, 2026·2 points·0 comments
AI Analysis
●●SolidBig BrainNiche Gem
In-process LLM inference in PHP beats the usual Python sidecar pattern.
Strengths
- •Rust bindings to llama-cpp-2 with ext-php-rs shows real technical depth
- •Latency argument is concrete: in-process calls bounded only by decode time
- •Fluent PHP API design matches native extensions like intl or pdo
Weaknesses
- •Pre-release status (v0.1.0 in flight) means production risk remains
- •PHP-only audience limits broader developer appeal
Category
Target Audience
PHP developers building AI features
Similar To
llama.cpp · Ollama · LM Studio
Similar Projects
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
204mo ago
AI/ML●●Solid
WayInfer – Native GGUF engine that runs models larger than your RAM
Custom GGUF parser with mmap beats llama.cpp load times, but zero stars means unproven claims.
WizardryBold Bet
ahmedm24
103mo ago
AI/ML●●Solid
TensorSharp: Open-Source Local LLM Inference Engine
Native .NET LLM inference when everything else forces you into Python.
Niche GemBig Brain
zhongkaifu
2012d ago
AI/ML●●●Banger
Valkyr LM Inference with Realtime Guarantees
Pure Vulkan compute enables LLMs inside game loops without CUDA lock-in.
WizardryNiche Gem
quatonion
302mo ago
Infrastructure●●Solid
LLM-Gateway – Zero-Trust LLM Gateway
Zero-trust networking via zrok beats LiteLLM when your GPUs sit behind NAT.
Big BrainSolve My Problem
michaelquigley
713mo ago