feat(ornith): bump context length 32K → 64K
V100-PCIE-32GB has ~12GB VRAM headroom after model weights. ornith:35b Q4_K_M KV cache at 64K ≈ 11.8GB — fits within budget. Model natively supports 256K but hardware caps safe limit at 64K.
This commit is contained in:
@@ -44,7 +44,7 @@ spec:
|
||||
- name: OLLAMA_MODELS
|
||||
value: /mnt/models/ollama
|
||||
- name: OLLAMA_CONTEXT_LENGTH
|
||||
value: '32768'
|
||||
value: '65536'
|
||||
- name: OLLAMA_KEEP_ALIVE
|
||||
value: '-1'
|
||||
- name: OLLAMA_NUM_PARALLEL
|
||||
|
||||
Reference in New Issue
Block a user