phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(provider): adding llama4 support in together inference provider (#2123)

Browse source 
# What does this PR do?
Adding Llama4 model support in TogetherAI provider
This commit is contained in:
Yogish Baliga 2025-05-08 14:27:56 -07:00 • committed by GitHub
parent fe5f5e530c
commit 0f878ad87a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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,

20
llama_stack/templates/together/run-with-safety.yaml
View file

@ -202,6 +202,26 @@ models:
provider_id: together
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
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
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
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
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 8192

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

@ -197,6 +197,26 @@ models:
provider_id: together
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
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
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
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
provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
model_type: llm
- metadata:
embedding_dimension: 768
context_length: 8192

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