phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 03:52:00 +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

8
llama_stack/providers/remote/inference/together/models.py
View file

@ -48,6 +48,14 @@ MODEL_ENTRIES = [
"meta-llama/Llama-Guard-3-11B-Vision-Turbo",
CoreModelId.llama_guard_3_11b_vision.value,
),
build_hf_repo_model_entry(
"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
CoreModelId.llama4_maverick_17b_128e_instruct.value,
),
build_hf_repo_model_entry(
"meta-llama/Llama-4-Scout-17B-16E-Instruct",
CoreModelId.llama4_scout_17b_16e_instruct.value,
),
ProviderModelEntry(
provider_model_id="togethercomputer/m2-bert-80M-8k-retrieval",
model_type=ModelType.embedding,