Download the PHP package displace/ext-infer without Composer
On this page you can find all versions of the php package displace/ext-infer. It is possible to download/install these versions without Composer. Possible dependencies are resolved automatically.
Download displace/ext-infer
More information about displace/ext-infer
Files in displace/ext-infer
Package ext-infer
Short Description PHP 8.3+ native, in-process LLM inference and embeddings via llama.cpp.
License MIT
Homepage https://github.com/DisplaceTech/ext-infer
FAQ
Example:
In general, it is recommended to use always a project to download your libraries. In an application normally there is more than one library needed.
- Some hosting areas are not accessible by a terminal or SSH. Then it is not possible to use Composer.
- To use Composer is sometimes complicated. Especially for beginners.
- Composer needs much resources. Sometimes they are not available on a simple webspace.
- If you are using private repositories you don't need to share your credentials. You can set up everything on our site and then you provide a simple download link to your team member.
- Simplify your Composer build process. Use our own command line tool to download the vendor folder as binary. This makes your build process faster and you don't need to expose your credentials for private repositories.
Informations about the package ext-infer
ext-infer
Local LLM inference for PHP, in-process.
Chat, embeddings, and reasoning models — no Python sidecar, no remote API.
What is ext-infer?
ext-infer is a PHP 8.3+ extension that loads a GGUF model and runs
inference in the PHP process via llama.cpp.
PHP-native semantic search, RAG pipelines, and CLI/worker inference work
without shelling out to Python or hitting a remote API.
Written in Rust on top of ext-php-rs
and the llama-cpp-2 bindings. The
public PHP surface is fluent and role-aware — building a chat prompt looks
like Prompt::system(...)->withUser(...), not a string of <|im_start|>
tokens.
- 💬 Chat completions via an immutable
Promptbuilder that renders through the model's embedded template — no manual<|im_start|>plumbing. - 🧱 Structured output — pass a JSON Schema (or raw GBNF grammar) and sampling is constrained so malformed output is impossible, not retried. A 0.6B model becomes a dependable extractor.
- 🧠 Reasoning-model aware —
Response::answer()andResponse::reasoning()split Qwen3 / R1-style<think>…</think>output automatically. - 📊 Embeddings —
Model::embed()returns anEmbeddingwithdimensions(),normalize(),cosineSimilarity(), andpacked()(zero-copy handoff to vector indexes) built in. - 🎯 Reranking —
RerankModelscores (query, document) pairs through Qwen3-Reranker's calibrated yes/no judgment; completes the embed → rerank two-stage retrieval pipeline. - ⚡ In-process — no subprocess fork, no IPC, no daemon. Latency is whatever the model takes to decode.
- 🛠️ Apple Metal acceleration is opt-in (
make release FEATURES=metal); CPU is the portable default. - 🧵 Thread-safe —
LlamaBackendis aSync-guarded singleton and each call builds its own context, so ZTS PHP +parallelworks by design.
Quick start
Full walkthrough — including the interactive Symfony Console
chat and pairwise-similarity embedding
example — under examples/.
Documentation
infer.displace.tech hosts the full guide:
- Getting started — install via PIE or from source, verify, troubleshoot.
- Guide — prompts, chat, raw, embeddings, choosing a model.
- Recipes — multi-turn chat, semantic search, RAG over markdown, worker pools.
- Reference — full API surface, exceptions, environment variables, compatibility matrix.
- Advanced — threading, Metal, performance tuning.
The site is built from mdbook
and deploys automatically on every push to main.
Compatibility
| macOS arm64 | Linux x86_64 | Linux arm64 | Windows | |
|---|---|---|---|---|
| PHP 8.3 | ✅ | ✅ | ✅ | — |
| PHP 8.4 | ✅ | ✅ | ✅ | — |
| PHP 8.5 | ✅ | ✅ | ✅ | — |
ZTS is supported by design (the code is thread-safe), enabled in
composer.json, and not yet exercised in CI. Windows is intentionally
out of scope for v0.1.
Roadmap
Shipped chat completions · raw completions · grammar/JSON-Schema constrained generation · embeddings (+ packed float32 output) · RerankModel · reasoning split · typed exceptions · PHPT suite · CI matrix · PIE-compatible composer.json · tag-triggered binary release workflow · THIRD-PARTY-NOTICES + cargo about license manifest.
Next (v0.3+) streaming completions · KV-cache reuse via reusable Session objects · stop-string support · LoRA adapters · tool calling · Apple Metal default on macos-arm64.
See RELEASE.md
for the cut-a-release flow.
License
MIT © 2026 Eric Mann / Displace Technologies
