containers/ramalama
1
0
Fork 0
mirror of https://github.com/containers/ramalama.git synced 2026-02-05 06:46:39 +01:00
Code Issues Wiki Activity

Fix typo in llama.cpp engine spec

Browse Source 
Signed-off-by: Oliver Walsh <owalsh@redhat.com>
This commit is contained in:
Oliver Walsh
2025-10-02 10:52:21 +01:00
parent ccc6e6a61f
commit 89cd6c360b
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
inference-spec/engines/llama.cpp.yaml
View File

@@ -58,7 +58,7 @@ commands:
- name: "--flash-attn"
description: "Set Flash Attention use"
value: "on"
if: "{{ host.uses_nvidia or host.uses_metal() }}"
if: "{{ host.uses_nvidia or host.uses_metal }}"
- name: "-ngl"
description: "Number of layers to offload to the GPU if available"
value: "{{ 999 if args.ngl < 0 else args.ngl }}"

2
test/unit/command/data/engines/llama.cpp.yaml
View File

@@ -58,7 +58,7 @@ commands:
- name: "--flash-attn"
description: "Set Flash Attention use"
value: "on"
if: "{{ host.uses_nvidia or host.uses_metal() }}"
if: "{{ host.uses_nvidia or host.uses_metal }}"
- name: "-ngl"
description: "Number of layers to offload to the GPU if available"
value: "{{ 999 if args.ngl < 0 else args.ngl }}"