phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-29 13:34:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add meta/llama-3.3-70b-instruct as supported nvidia inference provider model

Browse source
This commit is contained in:
Matthew Farrellee 2025-04-17 09:08:57 -04:00
parent 2ae1d7f4e6
commit e466962e11
3 changed files with 15 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/templates/nvidia/run.yaml
View file

@ -173,6 +173,16 @@ models:
provider_id: nvidia
provider_model_id: meta/llama-3.2-90b-vision-instruct
model_type: llm
- metadata: {}
model_id: meta/llama-3.3-70b-instruct
provider_id: nvidia
provider_model_id: meta/llama-3.3-70b-instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-3.3-70B-Instruct
provider_id: nvidia
provider_model_id: meta/llama-3.3-70b-instruct
model_type: llm
- metadata:
embedding_dimension: 2048
context_length: 8192