phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 15:59:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixes after rebase

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-12 15:37:07 -08:00
parent 948f6ece6e
commit 919d421bcf
11 changed files with 72 additions and 70 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/remote/inference/bedrock/bedrock.py
View file

@ -26,15 +26,15 @@ from llama_stack.providers.utils.bedrock.client import create_bedrock_client
model_aliases = [
build_model_alias(
"meta.llama3-1-8b-instruct-v1:0",
CoreModelId.llama3_1_8b_instruct,
CoreModelId.llama3_1_8b_instruct.value,
),
build_model_alias(
"meta.llama3-1-70b-instruct-v1:0",
CoreModelId.llama3_1_70b_instruct,
CoreModelId.llama3_1_70b_instruct.value,
),
build_model_alias(
"meta.llama3-1-405b-instruct-v1:0",
CoreModelId.llama3_1_405b_instruct,
CoreModelId.llama3_1_405b_instruct.value,
),
]

4
llama_stack/providers/remote/inference/databricks/databricks.py
View file

@ -36,11 +36,11 @@ from .config import DatabricksImplConfig
model_aliases = [
build_model_alias(
"databricks-meta-llama-3-1-70b-instruct",
CoreModelId.llama3_1_70b_instruct,
CoreModelId.llama3_1_70b_instruct.value,
),
build_model_alias(
"databricks-meta-llama-3-1-405b-instruct",
CoreModelId.llama3_1_405b_instruct,
CoreModelId.llama3_1_405b_instruct.value,
),
]

18
llama_stack/providers/remote/inference/fireworks/fireworks.py
View file

@ -38,39 +38,39 @@ from .config import FireworksImplConfig
model_aliases = [
build_model_alias(
"fireworks/llama-v3p1-8b-instruct",
CoreModelId.llama3_1_8b_instruct,
CoreModelId.llama3_1_8b_instruct.value,
),
build_model_alias(
"fireworks/llama-v3p1-70b-instruct",
CoreModelId.llama3_1_70b_instruct,
CoreModelId.llama3_1_70b_instruct.value,
),
build_model_alias(
"fireworks/llama-v3p1-405b-instruct",
CoreModelId.llama3_1_405b_instruct,
CoreModelId.llama3_1_405b_instruct.value,
),
build_model_alias(
"fireworks/llama-v3p2-1b-instruct",
CoreModelId.llama3_2_3b_instruct,
CoreModelId.llama3_2_3b_instruct.value,
),
build_model_alias(
"fireworks/llama-v3p2-3b-instruct",
CoreModelId.llama3_2_11b_vision_instruct,
CoreModelId.llama3_2_11b_vision_instruct.value,
),
build_model_alias(
"fireworks/llama-v3p2-11b-vision-instruct",
CoreModelId.llama3_2_11b_vision_instruct,
CoreModelId.llama3_2_11b_vision_instruct.value,
),
build_model_alias(
"fireworks/llama-v3p2-90b-vision-instruct",
CoreModelId.llama3_2_90b_vision_instruct,
CoreModelId.llama3_2_90b_vision_instruct.value,
),
build_model_alias(
"fireworks/llama-guard-3-8b",
CoreModelId.llama_guard_3_8b,
CoreModelId.llama_guard_3_8b.value,
),
build_model_alias(
"fireworks/llama-guard-3-11b-vision",
CoreModelId.llama_guard_3_11b_vision,
CoreModelId.llama_guard_3_11b_vision.value,
),
]

15
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -42,31 +42,31 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
model_aliases = [
build_model_alias(
"llama3.1:8b-instruct-fp16",
CoreModelId.llama3_1_8b_instruct,
CoreModelId.llama3_1_8b_instruct.value,
),
build_model_alias(
"llama3.1:70b-instruct-fp16",
CoreModelId.llama3_1_70b_instruct,
CoreModelId.llama3_1_70b_instruct.value,
),
build_model_alias(
"llama3.2:1b-instruct-fp16",
CoreModelId.llama3_2_1b_instruct,
CoreModelId.llama3_2_1b_instruct.value,
),
build_model_alias(
"llama3.2:3b-instruct-fp16",
CoreModelId.llama3_2_3b_instruct,
CoreModelId.llama3_2_3b_instruct.value,
),
build_model_alias(
"llama-guard3:8b",
CoreModelId.llama_guard_3_8b,
CoreModelId.llama_guard_3_8b.value,
),
build_model_alias(
"llama-guard3:1b",
CoreModelId.llama_guard_3_1b,
CoreModelId.llama_guard_3_1b.value,
),
build_model_alias(
"x/llama3.2-vision:11b-instruct-fp16",
CoreModelId.llama3_2_11b_vision_instruct,
CoreModelId.llama3_2_11b_vision_instruct.value,
),
]
@ -164,6 +164,7 @@ class OllamaInferenceAdapter(Inference, ModelRegistryHelper, ModelsProtocolPriva
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
model = await self.model_store.get_model(model_id)
print(f"model={model}")
request = ChatCompletionRequest(
model=model.provider_resource_id,
messages=messages,

16
llama_stack/providers/remote/inference/together/together.py
View file

@ -41,35 +41,35 @@ from .config import TogetherImplConfig
model_aliases = [
build_model_alias(
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
CoreModelId.llama3_1_8b_instruct,
CoreModelId.llama3_1_8b_instruct.value,
),
build_model_alias(
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
CoreModelId.llama3_1_70b_instruct,
CoreModelId.llama3_1_70b_instruct.value,
),
build_model_alias(
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
CoreModelId.llama3_1_405b_instruct,
CoreModelId.llama3_1_405b_instruct.value,
),
build_model_alias(
"meta-llama/Llama-3.2-3B-Instruct-Turbo",
CoreModelId.llama3_2_3b_instruct,
CoreModelId.llama3_2_3b_instruct.value,
),
build_model_alias(
"meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
CoreModelId.llama3_2_11b_vision_instruct,
CoreModelId.llama3_2_11b_vision_instruct.value,
),
build_model_alias(
"meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
CoreModelId.llama3_2_90b_vision_instruct,
CoreModelId.llama3_2_90b_vision_instruct.value,
),
build_model_alias(
"meta-llama/Meta-Llama-Guard-3-8B",
CoreModelId.llama_guard_3_8b,
CoreModelId.llama_guard_3_8b.value,
),
build_model_alias(
"meta-llama/Llama-Guard-3-11B-Vision-Turbo",
CoreModelId.llama_guard_3_11b_vision,
CoreModelId.llama_guard_3_11b_vision.value,
),
]

3
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -38,7 +38,7 @@ def build_model_aliases():
return [
build_model_alias(
model.huggingface_repo,
model.core_model_id,
model.descriptor(),
)
for model in all_registered_models()
if model.huggingface_repo
@ -85,6 +85,7 @@ class VLLMInferenceAdapter(Inference, ModelRegistryHelper, ModelsProtocolPrivate
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
model = await self.model_store.get_model(model_id)
print(f"model={model}")
request = ChatCompletionRequest(
model=model.provider_resource_id,
messages=messages,