riotpiao-poimen/homelab
2
0
Fork 0
Code Issues 24 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

k8s(llm-serving): stop managing the coder InferenceService (#106)

Browse Source 
Co-authored-by: rock <[email protected]>
This commit was merged in pull request #106.
This commit is contained in:
rock
2026-11-03 22:07:52 +00:00
committed by rock
parent 6b609eb4c2
commit c5099e3a8f
1 changed files with 0 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
k8s/apps/llm-serving/kustomization.yaml
-5
View File
@@ -14,11 +14,6 @@ resources:
# v0.5.22+, published only on CUDA 13, and CUDA 13 dropped Volta kernels. The model # v0.5.22+, published only on CUDA 13, and CUDA 13 dropped Volta kernels. The model
# instead runs the implementation it ships (joint_schema_model.py) in fp16 on one V100. # instead runs the implementation it ships (joint_schema_model.py) in fp16 on one V100.
- clef-serve.yaml - clef-serve.yaml
# coder = Qwen3-Coder-30B-A3B-Instruct, 4-bit GPTQ, TP=2 at 262,144 tokens. It serves
# both `coder` and `reasoning`, so poimen-memory needs a host change only, never a
# model-name change. reasoning.yaml below can be dropped once that host change lands.
- coder.yaml
- reasoning.yaml
# Stable client-facing name for the chat model. poimen-memory points at this Service, # Stable client-facing name for the chat model. poimen-memory points at this Service,
# so the vLLM -> candle-vllm handoff is a selector edit here and no client change. # so the vLLM -> candle-vllm handoff is a selector edit here and no client change.
- reasoning-long-service.yaml - reasoning-long-service.yaml