Skip to content

Llmff

v0.1.3 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 11d LLM Frameworks
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

Adds schema contracts, provider examples, execution controls, and supervision tooling for stable pipeline workflows.

Full changelog

llmff v0.1.3

Ecosystem-maturity release for agent and automation workflows. This release
keeps the GitHub Release asset lane from v0.1.2 and adds the schema,
plugin, provider, supervision, execution, and documentation surfaces needed for
downstream tools to treat llmff as a stable subprocess pipeline runner.

Supported Install

cargo install --git https://github.com/syndicalt/llmff --tag v0.1.3 llmff

Included Since v0.1.2

  • Published schema v1 contracts for pipeline manifests, traces, lifecycle
    events, plugin manifests, and plugin validation reports.
  • Golden schema fixtures plus scripts/check-schema-contract.py for contract
    validation.
  • Provider examples for OpenAI, Azure OpenAI, LM Studio, vLLM, LocalAI,
    OpenRouter, Together, Groq, and Anthropic-compatible adapter usage.
  • Opt-in live provider smoke workflow for OpenAI-compatible and Ollama
    endpoints.
  • llmff backends report for backend capability and configuration reporting.
  • Plugin protocol v1 fixtures, static registry documentation, and trust review
    guidance.
  • Example plugins for retrieval, reranking, model backend, sampler, tool
    transport, and postprocessor-as-stage patterns.
  • Production-oriented pipeline templates for summarization, extraction,
    classification, JSON repair, RAG, batch processing, tool calling, eval
    harnesses, multi-provider fallback, and cost/latency comparison.
  • Execution controls for safe failure classification, retry/backoff, per-stage
    and default timeouts, concurrency limits, batch input, checkpoint/resume,
    cache policy, and guarded trace replay.
  • Trace summary and Prometheus-style metrics exporters for local supervision.
  • Agent workflow documentation and a runnable Python subprocess supervisor
    example.
  • Governance, stability, release compatibility, and deprecation policies for
    the documented contracts.

Packaged Artifacts

Release-tag CI is expected to publish:

  • Linux x86_64 .tar.gz archive, .deb package, and Arch PKGBUILD plus
    llmff-0.1.3-arch.SRCINFO metadata.
  • macOS Apple Silicon and Intel .tar.gz archives and unsigned .pkg
    installers.
  • Windows x86_64 unsigned .zip archive and unsigned MSI installer.
  • Adjacent SHA-256 checksums for generated binary artifacts.

Manual workflow dispatch keeps generated files as Actions artifacts instead of
GitHub Release assets.

Known Limitations

  • This is a pipeline runner, not a native inference kernel, model converter,
    serving platform, or full agent framework.
  • Windows and macOS native artifacts are unsigned in this release.
  • Package-manager distribution through Homebrew, winget, Scoop, apt
    repositories, or an official AUR package remains parked until maintainers
    decide those channels are support-ready.
  • Authenticode signing, Apple Developer ID signing, and notarization remain
    deferred paid distribution tracks.
  • Live provider smoke jobs remain opt-in and require maintainers to configure
    secrets and runner expectations explicitly.

Verification

Release verification should pass before tagging:

scripts/release-preflight.sh v0.1.3
scripts/smoke-install.sh --git https://github.com/syndicalt/llmff --tag v0.1.3

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track Llmff

Get notified when new releases ship.

Sign up free

About Llmff

All releases →

Beta — feedback welcome: [email protected]