From 7dc4f786f1acdd410482c71715c25ed09dbc55c0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ignacio=20L=C3=B3pez=20Luna?= Date: Wed, 10 Jun 2026 15:29:15 +0200 Subject: [PATCH 1/2] chore: bump llama.cpp to b9592 Co-Authored-By: Claude Opus 4.8 (1M context) --- .versions | 2 +- Dockerfile | 4 ++-- llamacpp/native/vendor/llama.cpp | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/.versions b/.versions index 17787665f..6d1999e17 100644 --- a/.versions +++ b/.versions @@ -5,4 +5,4 @@ VLLM_UPSTREAM_VERSION=0.19.0 VLLM_METAL_RELEASE=v0.2.0-20260420-142150 DIFFUSERS_RELEASE=v0.1.0-20260216-000000 SGLANG_VERSION=0.5.6 -LLAMA_SERVER_VERSION=b9501 +LLAMA_SERVER_VERSION=b9592 diff --git a/Dockerfile b/Dockerfile index 7b829a12f..7b305256f 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,9 +1,9 @@ # syntax=docker/dockerfile:1 ARG GO_VERSION=1.25 -ARG LLAMA_SERVER_VERSION=b9501 +ARG LLAMA_SERVER_VERSION=b9592 ARG LLAMA_SERVER_VARIANT=cpu -ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b9501 +ARG LLAMA_UPSTREAM_IMAGE=ghcr.io/ggml-org/llama.cpp:server-vulkan-b9592 ARG VERSION=dev diff --git a/llamacpp/native/vendor/llama.cpp b/llamacpp/native/vendor/llama.cpp index 65ef50a0a..ac4cddeb0 160000 --- a/llamacpp/native/vendor/llama.cpp +++ b/llamacpp/native/vendor/llama.cpp @@ -1 +1 @@ -Subproject commit 65ef50a0a4bb240211a41d43c957ae6313af6841 +Subproject commit ac4cddeb0dbd778f650bf568f6f08344a06abe3a From 4a7057be3652355af0052a4c09ae74da5be24fa9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ignacio=20L=C3=B3pez=20Luna?= Date: Thu, 11 Jun 2026 11:04:47 +0200 Subject: [PATCH 2/2] ci(release): prune cloud builder cache before building MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The release job builds 7 image variants on a single shared Docker Build Cloud builder. Accumulated cache from previous runs eventually fills the builder's disk, surfacing as "no space left on device" while unpacking the (growing) upstream llama.cpp image snapshots — which is what broke the b9592 release. Add a `docker buildx prune -af` step right after Set up Buildx so each release starts with a clean builder disk. Co-Authored-By: Claude Opus 4.8 (1M context) --- .github/workflows/release.yml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index 60e35a246..897d67566 100644 --- a/.github/workflows/release.yml +++ b/.github/workflows/release.yml @@ -311,6 +311,7 @@ jobs: password: ${{ secrets.ORG_ACCESS_TOKEN }} - name: Set up Buildx + id: buildx uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0 with: version: "lab:latest" @@ -318,6 +319,14 @@ jobs: endpoint: "docker/make-product-smarter" install: true + # Purge the shared cloud builder's cache before building. The release + # builds 7 image variants (cpu/cuda on amd64+arm64) on one cloud builder, + # and accumulated cache from previous runs eventually fills its disk — + # surfacing as "no space left on device" while unpacking the (growing) + # upstream llama.cpp image snapshots. Starting clean avoids that. + - name: Free build cache on cloud builder + run: docker buildx prune -af --builder ${{ steps.buildx.outputs.name }} + - name: Build CPU image uses: docker/build-push-action@f9f3042f7e2789586610d6e8b85c8f03e5195baf with: