b9747

ggml-org/llama.cppb9747Jun 21, 2026by github-actions[bot]same day as b9745

What changed since b9745

low risk

Adds a server-sent events endpoint /models/sse for real-time model load progress tracking.

New features

  • New /models/sse SSE endpoint streams live model loading progress to clients.
  • Server monitoring now supports subscribing to load-progress events instead of polling.

Improvements

  • Added a mutex around notify_to_router to make router notifications thread-safe.
  • Documentation updated to describe the new SSE endpoint.

Upgrade notes

This is a small delta over b9745: the only functional addition is the /models/sse endpoint, so no config or API migrations are required. Clients that poll for model status can optionally switch to the SSE stream; existing endpoints remain unchanged.

Analyzed Nov 1, 2026

Upgrading?

Release notes summary

Adds real-time model loading progress tracking via a new Server-Sent Events (SSE) endpoint /models/sse in the server.

Key Highlights

  • Real-time model load progress tracking
  • New SSE endpoint /models/sse for monitoring
  • Adds mutex for notify_to_router

Release Notes (excerpt)

<details open> server: real-time model load progress tracking via /models/sse (#24828) * server: real-time model load progress tracking via /models/sse * update docs * add mutex for notify_to_router * correct docs </details> **macOS/iOS:** - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework **Linux:** - Ubuntu x64 (CPU) - Ubuntu arm64 (CPU) - Ubuntu s390x (CPU) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories