Starstruk Logo MarkStarstruk

v0.72.0

Mesh-LLM/mesh-llmv0.72.0Jun 30, 2026by github-actions[bot]

AI Summary

This release marks a significant milestone with the launch of the public website and documentation, alongside major improvements to Skippy split serving performance and native runtime packaging reliability.

Key Highlights

  • Launch of public website (meshllm.cloud), catalog viewer, and refreshed documentation.
  • Hardened native runtime packaging with CUDA profile detection and Windows support.
  • Improved Skippy split serving with latency-aware stage planning and repeated-prompt cache replay.
  • Expanded model packaging with native `skippy-quantize` CLI support and GLM DSA IndexShare support.

New Features

  • public meshllm.cloud website
  • Skippy latency-aware stage planning
  • schema-driven configuration controls
  • native Rust SDK
  • schema-driven runtime and network settings

Full Release Notes

# v0.72.0

## Highlights

- Added the public [meshllm.cloud](https://meshllm.cloud) website, catalog viewer, onboarding docs, canonical docs URLs, and refreshed install documentation.
- Hardened release packaging around versioned native runtimes, explicit runtime version selection, release-matrix validation, runtime install smoke checks, relocatable shared libraries, CUDA profile detection, and Windows runtime packaging.
- Improved Skippy split serving with latency-aware stage planning, faster decode return paths, topology-aware prefill chunking, repeated-prompt cache replay, KV pressure fixes, cache epoch telemetry, stage role metadata, and native runtime event visibility.
- Expanded model packaging and conversion flows with native `skippy-quantize` conversion/quantization CLI support, direct quantized layer package workflows, inline package-writer/download progress, native MTP metadata, GLM DSA IndexShare support, and GLM-DSA crash fixes.
- Strengthened mesh routing and reliability with LAN-only mDNS hardening, bounded direct-path repair, iroh 1.0, stale split topology withdrawal, local target reputation routing, split-startup diagnostics, and safer model reconciliation.
- Improved MoA and OpenAI-compatible behavior for agent/tool loops, including committed Responses streaming, usable-contributor context advertisement, small-model consensus safeguards, low-quality response retries, and chat/thinking fixes.
- Revamped configuration with schema-driven controls, clearer runtime/model/network settings, validation diagnostics, UI-backed config behavior, and more realistic control surfaces.
- Improved SDK and embedding surfaces, including the native Rust SDK, native runtime install APIs, SDK packaging updates, and refreshed Node/Swift/Kotlin bindings.
- Fixed Windows installer and binary compatibility issues, including PowerShell 5.1 `irm | iex`, missing checksum sidecars, and crashes on CPUs without AVX-512.
- Tightened CI and release workflows with restored PR gates, sccache build-script support, native runtime matrix checks, nightly stability fixes, HF model cache/smoke hardening, and faster release builds.

## Notable Fixes

- Fixed CUDA runtime profile detection for release/native-runtime selection.
- Fixed release publish credential preservation and Windows CUDA runtime DLL handling.
- Fixed chat system prompt feature flag gating.
- Fixed model deletion cleanup for broken `hf_hub` cache symlinks.
- Fixed `/api/models` repeatedly re-downloading catalog data.
- Fixed GPU CLI stderr behavior and improved TUI panic/debug capture.
- Fixed insecure-origin chat ID behavior.
- Fixed Metal Skippy shutdown race.
- Fixed release version stamping and runtime startup initialization.

## Contributors

Thanks to @IvGolovach, @i386, @michaelneale, @ndizazzo, and first-time contributor @wesbillman.

## Full Changelog

- Current run compare: https://github.com/Mesh-LLM/mesh-llm/compare/v0.71.0...100f54806b0b47b23e5eb26b1ec6b5cb591025f8
- Final tag compare, once published: https://github.com/Mesh-LLM/mesh-llm/compare/v0.71.0...v0.72.0