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

# What does this PR do?
Adding Llama4 model support in TogetherAI provider

docs/source/distributions/self_hosted_distro/together.md

@@ -46,6 +46,8 @@ The following models are available by default:
 - `meta-llama/Llama-3.3-70B-Instruct-Turbo (aliases: meta-llama/Llama-3.3-70B-Instruct)`
 - `meta-llama/Meta-Llama-Guard-3-8B (aliases: meta-llama/Llama-Guard-3-8B)`
 - `meta-llama/Llama-Guard-3-11B-Vision-Turbo (aliases: meta-llama/Llama-Guard-3-11B-Vision)`
+- `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 (aliases: meta-llama/Llama-4-Maverick-17B-128E-Instruct)`
+- `meta-llama/Llama-4-Scout-17B-16E-Instruct (aliases: meta-llama/Llama-4-Scout-17B-16E-Instruct)`
 - `togethercomputer/m2-bert-80M-8k-retrieval `
 - `togethercomputer/m2-bert-80M-32k-retrieval `
 - `meta-llama/Llama-4-Scout-17B-16E-Instruct (aliases: meta-llama/Llama-4-Scout-17B-16E-Instruct, together/meta-llama/Llama-4-Scout-17B-16E-Instruct)`

llama_stack/providers/remote/inference/together/models.py

@@ -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,

llama_stack/templates/together/run-with-safety.yaml

@@ -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

llama_stack/templates/together/run.yaml

@@ -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

llama_stack/templates/verification/run.yaml

@@ -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