Skip to content

fix(container): update image ghcr.io/ggml-org/llama.cpp (f862c90 ➔ 9b67d4b) #4875

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Tanguille merged 1 commit into from
Sep 6, 2026
+3 −3
Merged

fix(container): update image ghcr.io/ggml-org/llama.cpp (f862c90 ➔ 9b67d4b) #4875

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion kubernetes/apps/ai/llmkube/models/qwen3-embedding.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ spec:
# Native upstream GTT-leak mitigation in LLMKube >=0.9.10; lifetime includes
# startup and model load before this Vulkan embedder is recycled.
maxPodLifetimeSeconds: 86400
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:f862c901a0089bc3dc326bd24f208bfcd147839783328d252e911a004c94ff3c
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:9b67d4b09614453f5511e655aa6a7792ddb16e93ae9116134c910bb1951da645
# Two slots are the Vulkan-safe floor; more interleaving did not improve
# throughput on this compute-bound iGPU. VMCP has its own embedder now.
parallelSlots: 2 # Vulkan warmup hangs at parallel=1 (llama.cpp #24307)
Expand Down
2 changes: 1 addition & 1 deletion kubernetes/apps/ai/llmkube/models/qwen35-2b.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ spec:
modelRef: qwen35-2b
# Must be recent enough for Qwen3.5's GDN (Gated Delta Networks) architecture;
# verified to load `qwen35` and run GDN fully on Vulkan (no CPU fallback).
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:f862c901a0089bc3dc326bd24f208bfcd147839783328d252e911a004c94ff3c
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:9b67d4b09614453f5511e655aa6a7792ddb16e93ae9116134c910bb1951da645
parallelSlots: 2 # Vulkan warmup hangs at parallel=1 (llama.cpp #24307)
# llama.cpp splits contextSize across parallelSlots, so 32768/2 = 16384 per slot.
# GDN keeps KV tiny, so long ctx is cheap; 16K per slot is plenty for offload.
Expand Down
2 changes: 1 addition & 1 deletion kubernetes/apps/ai/llmkube/models/vmcp-embedding.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@ spec:
# reloading at once on control-3 is the condition behind the podAffinity
# deadlock; offsetting the period drops realignment from daily to every 3d.
maxPodLifetimeSeconds: 64800
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:f862c901a0089bc3dc326bd24f208bfcd147839783328d252e911a004c94ff3c
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:9b67d4b09614453f5511e655aa6a7792ddb16e93ae9116134c910bb1951da645
# Vulkan floor is 2 — warmup hangs at parallel=1 (llama.cpp #24307). The iGPU
# is compute-bound, so more slots add interleave, not throughput.
parallelSlots: 2
Expand Down