Skip to content

fix(container): update image ghcr.io/ggml-org/llama.cpp (e7249fa ➔ eddb40b) #4190

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
Jul 27, 2026
Merged

fix(container): update image ghcr.io/ggml-org/llama.cpp (e7249fa ➔ eddb40b) #4190

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 @@ -38,7 +38,7 @@ 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:e7249fa3c18189a825898832cc4d722d7f9c0160c29540ced793c833ab9f2432
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:eddb40b8a348a652c8829ef036df9bbbae537755ae7026bf6d4b403840cd468e
# 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 @@ -32,7 +32,7 @@ spec:
# 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).
# Tracked by the llmkube-models Renovate customManager (.renovaterc.json5).
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:e7249fa3c18189a825898832cc4d722d7f9c0160c29540ced793c833ab9f2432
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:eddb40b8a348a652c8829ef036df9bbbae537755ae7026bf6d4b403840cd468e
parallelSlots: 2 # Vulkan warmup hangs at parallel=1 (llama.cpp #24307)
contextSize: 16384 # GDN keeps KV tiny, so long ctx is cheap; 16K is plenty for offload
jinja: true # use the model's chat template (correct Qwen3.5 formatting + tool calls)
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 @@ -50,7 +50,7 @@ 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:e7249fa3c18189a825898832cc4d722d7f9c0160c29540ced793c833ab9f2432
image: ghcr.io/ggml-org/llama.cpp:server-vulkan@sha256:eddb40b8a348a652c8829ef036df9bbbae537755ae7026bf6d4b403840cd468e
# 2 slots (the Vulkan floor — warmup hangs at parallel=1, llama.cpp #24307):
# the iGPU is compute-bound, so extra slots add interleave, not throughput
# (measured on qwen3-embedding: 4 slots didn't move latency, Q8_0 did). Two
Expand Down