llama.cpp v1.0.0: Image-Pin auf server-rocm-v1.0.0-b12359-b1b770d heben (GNAI-010 0.20)
ci-static / secret-scan (push) Successful in 21s
ci-static / yamllint (push) Successful in 31s
ci-static / ansible-syntax (push) Successful in 27s
ci-static / markdown-links (push) Successful in 20s
ci-static / secret-scan (pull_request) Successful in 21s
ci-static / yamllint (pull_request) Successful in 44s
ci-static / ansible-syntax (pull_request) Successful in 1m3s
ci-static / markdown-links (pull_request) Successful in 23s

- inference_engine + rocm_container_probe: Digest sha256:4bbbd2e3... (amd64-Manifest
  sha256:abb28972...), Build b12359, Revision b1b770d90..., OCI-Version
  v1.0.0-b12359-b1b770d. v1.0.0 (Release 13.11.2026) loest ueber nightly-tag.txt
  auf b12359 auf; moving tag server-rocm zeigt auf denselben Digest. Semver-Policy
  upstream ab v1.0.0 — passt zur Digest-Pinning-Konvention.
- Kompatibilitaet gegen b12359 llama-server --help geprueft (Image lokal gepullt):
  alle 26 Exec=-Flags des Quadlets existieren; einzige entfernte Option
  --defrag-thold (#30565) wird nicht verwendet. ENTRYPOINT /app/llama-server
  unveraendert. Server-Haertung #32113/#32115/#32098 greift nicht (kein
  server-seitiges --tools/MCP, keine privaten Media-URLs, OpenWebUI ist
  Non-Browser-Client). libllama.so.1/36 entfernte Symbole betreffen nur native
  Bindings — wir sind HTTP-only.
- Neue Optionen bewertet (GNAI-010 0.20): FP8-KV f8_e4m3 (auf gfx1030 emuliert,
  Benchmark vor Adoption, Default q8_0), --moe-cache-cpu-share (nur MoE),
  --sleep-idle-seconds (kontraproduktiv), --api-key (optional), die Opt-out-Flags
  --allow-unauthenticated-tools/--media-allow-private-urls bleiben aus.
- Doku: GNAI-010 v0.20 + Abschnitt 3.1, GNAI-008 v0.23 + Probe-Abschnitt,
  Host-README Pin-Block (alter Pin als historisch markiert).
- Quadlet Exec bleibt unveraendert. Rollout auf 10.0.0.90 steht noch aus.

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
This commit is contained in:
2026-11-14 15:04:14 +01:00
parent 004ef9f744
commit 8480d53349
5 changed files with 38 additions and 21 deletions
+7 -3
View File
@@ -204,11 +204,15 @@ The dedicated verification playbook uses `gnai-testing` and an immutable amd64
manifest of the official `llama.cpp` ROCm image:
```text
version: b11058
revision: f072b103714dfa1eee531f80b24512faf38e3dd2
digest: sha256:b429b8be10d3d0353a09c98f4ab840fe516f779858a28f9fd4e5bdf10bc63cb4
version: v1.0.0-b12359-b1b770d # OCI label; release tag v1.0.0 (2026-11-13), build b12359
revision: b1b770d90d94cad9e9ea5b993bdbc383a522fb28
digest: sha256:4bbbd2e33deb54330fd23edde3a2cdf12b05ce4415139c7e8639a9aebbacdcf2
```
Updated 2026-11-14 from the previous pin `b11058` / `f072b103…` /
`sha256:b429b8be…` to the v1.0.0 stable tag (`server-rocm-v1.0.0-b12359-b1b770d`,
amd64 manifest `sha256:abb28972…`).
It passes `/dev/kfd` and both discovered render nodes with
`--group-add=keep-groups`. `rocminfo` must report exactly two `gfx1030` agents,
and `llama-server --list-devices` must expose exactly two ROCm devices. No
@@ -4,9 +4,11 @@ rocm_probe_account:
uid: 981
home: /var/lib/ghostnet-ai/testing
# 2026-11-14: pin moved to the v1.0.0 stable tag (build b12359, commit
# b1b770d90); OCI label version of that image is v1.0.0-b12359-b1b770d.
rocm_probe_image: >-
ghcr.io/ggml-org/llama.cpp@sha256:b429b8be10d3d0353a09c98f4ab840fe516f779858a28f9fd4e5bdf10bc63cb4
rocm_probe_expected_image_revision: f072b103714dfa1eee531f80b24512faf38e3dd2
rocm_probe_expected_image_version: b11058
ghcr.io/ggml-org/llama.cpp@sha256:4bbbd2e33deb54330fd23edde3a2cdf12b05ce4415139c7e8639a9aebbacdcf2
rocm_probe_expected_image_revision: b1b770d90d94cad9e9ea5b993bdbc383a522fb28
rocm_probe_expected_image_version: v1.0.0-b12359-b1b770d
rocm_probe_expected_architecture: gfx1030
rocm_probe_expected_device_count: 2
@@ -4,10 +4,16 @@
# Experimental candidate and is intentionally not modelled here yet.
#
# Container image: immutable digest, never a moving tag (GNAI-010 section 3.1).
inference_engine_image: ghcr.io/ggml-org/llama.cpp:server-rocm
inference_engine_image_ref: ghcr.io/ggml-org/llama.cpp@sha256:b429b8be10d3d0353a09c98f4ab840fe516f779858a28f9fd4e5bdf10bc63cb4
inference_engine_image_build: "b11058"
inference_engine_image_revision: f072b103714dfa1eee531f80b24512faf38e3dd2
# 2026-11-14: pin moved to the v1.0.0 stable tag (released 2026-11-13), resolved
# via the release asset nightly-tag.txt to build b12359; the moving tag
# `server-rocm` already points at the same digest. All Exec flags of the quadlet
# were verified against `llama-server --help` of b12359 — the only removed flag
# is --defrag-thold (unused here). OCI labels: version v1.0.0-b12359-b1b770d,
# revision b1b770d90d94cad9e9ea5b993bdbc383a522fb28.
inference_engine_image: ghcr.io/ggml-org/llama.cpp:server-rocm-v1.0.0-b12359-b1b770d
inference_engine_image_ref: ghcr.io/ggml-org/llama.cpp@sha256:4bbbd2e33deb54330fd23edde3a2cdf12b05ce4415139c7e8639a9aebbacdcf2
inference_engine_image_build: "b12359"
inference_engine_image_revision: b1b770d90d94cad9e9ea5b993bdbc383a522fb28
# Environment identity (overridden per inventory, GNAI-008 section 7.4).
inference_engine_user: gnai-testing