phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 12:48:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

temp commit

Browse source
This commit is contained in:
Botao Chen 2024-12-16 19:04:47 -08:00
parent b2dbb5e3fe
commit 30f6eb282f
7 changed files with 16 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/templates/meta-reference-quantized-gpu/run.yaml
View file

@ -16,7 +16,7 @@ providers:
- provider_id: meta-reference-inference
provider_type: inline::meta-reference-quantized
config:
model: ${env.INFERENCE_MODEL}
model: ${env.INFERENCE_MODEL} # please make sure your inference model here is added as resource
max_seq_len: 4096
checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
quantization: