b9909

ggml-org/llama.cppb9909Jul 8, 2026by github-actions[bot]same day as b9908

What changed since b9908

low risk

b9909 adds timing and progress metrics to the /responses API stream; no other changes noted versus b9908.

New features

  • The /responses streaming endpoint now emits detailed timing metrics alongside generated output.
  • Progress updates are included in the /responses stream so clients can track generation status.

Improvements

  • Improved observability for streaming responses via richer per-stream telemetry.

Upgrade notes

No configuration or CLI changes are required; the prior b9908 cache-RAM behavior carries over unchanged. Clients that strictly parse /responses stream payloads should be updated to tolerate the new timing and progress fields/events rather than assuming a fixed schema.

Analyzed Oct 31, 2026

Upgrading?

Release notes summary

Enhances the `/responses` API stream endpoint by providing detailed timing metrics and progress updates to improve observability for users.

Key Highlights

  • Add timings and progress data to `/responses` API stream
  • Improves observability for streaming responses

Release Notes (excerpt)

<details open> server : add timings and progress to /responses API stream (#25348) </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) - Ubuntu x64 (ROCm 7.2) - Ubuntu x64 (OpenVINO) - Ubuntu x64 (SYCL FP32) - Ubuntu x64 (SYCL FP16) **Android:** - Android arm64 (CPU)…

Published by ggml-org on GitHub.

Read the full release notes

Related Repositories