phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-21 12:09:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into nvidia-e2e-notebook

Browse source
This commit is contained in:
Jash Gulabrai 2025-04-15 08:38:41 -04:00
commit 7cdd2a0410
264 changed files with 229042 additions and 8445 deletions
Download patch file Download diff file Expand all files Collapse all files

65
llama_stack/providers/registry/inference.py
View file

@ -24,6 +24,8 @@ META_REFERENCE_DEPS = [
"zmq",
"lm-format-enforcer",
"sentence-transformers",
"torchao==0.8.0",
"fbgemm-gpu-genai==1.1.2",
]
@ -36,19 +38,6 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.inline.inference.meta_reference",
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
),
InlineProviderSpec(
api=Api.inference,
provider_type="inline::meta-reference-quantized",
pip_packages=(
META_REFERENCE_DEPS
+ [
"fbgemm-gpu",
"torchao==0.5.0",
]
),
module="llama_stack.providers.inline.inference.meta_reference",
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceQuantizedInferenceConfig",
),
InlineProviderSpec(
api=Api.inference,
provider_type="inline::vllm",
@ -228,6 +217,56 @@ def available_providers() -> List[ProviderSpec]:
provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="fireworks-openai-compat",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.fireworks_openai_compat",
config_class="llama_stack.providers.remote.inference.fireworks_openai_compat.config.FireworksCompatConfig",
provider_data_validator="llama_stack.providers.remote.inference.fireworks_openai_compat.config.FireworksProviderDataValidator",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="together-openai-compat",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.together_openai_compat",
config_class="llama_stack.providers.remote.inference.together_openai_compat.config.TogetherCompatConfig",
provider_data_validator="llama_stack.providers.remote.inference.together_openai_compat.config.TogetherProviderDataValidator",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="groq-openai-compat",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.groq_openai_compat",
config_class="llama_stack.providers.remote.inference.groq_openai_compat.config.GroqCompatConfig",
provider_data_validator="llama_stack.providers.remote.inference.groq_openai_compat.config.GroqProviderDataValidator",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="sambanova-openai-compat",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.sambanova_openai_compat",
config_class="llama_stack.providers.remote.inference.sambanova_openai_compat.config.SambaNovaCompatConfig",
provider_data_validator="llama_stack.providers.remote.inference.sambanova_openai_compat.config.SambaNovaProviderDataValidator",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="cerebras-openai-compat",
pip_packages=["litellm"],
module="llama_stack.providers.remote.inference.cerebras_openai_compat",
config_class="llama_stack.providers.remote.inference.cerebras_openai_compat.config.CerebrasCompatConfig",
provider_data_validator="llama_stack.providers.remote.inference.cerebras_openai_compat.config.CerebrasProviderDataValidator",
),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(