phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 23:41:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

adding llama4 support in together inference provider

Browse source
This commit is contained in:
Yogish Baliga 2025-05-08 14:16:35 -07:00
parent fe5f5e530c
commit af6f7bc535
5 changed files with 70 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

20
llama_stack/templates/verification/run.yaml
View file

@ -372,6 +372,26 @@ models:
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata: {}
model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
provider_id: together-openai-compat
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 8192