mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-20 19:56:59 +00:00
chore: kill inline::vllm (#2824)
Inline _inference_ providers haven't proved to be very useful -- they
are rarely used. And for good reason -- it is almost never a good idea
to include a complex (distributed) inference engine bundled into a
distributed stateful front-end server serving many other things.
Responsibility should be split properly.
See Discord discussion:
1395849853
This commit is contained in:
Ashwin Bharambe
GitHub
parent
68a2dfbad7
commit
ade075152e
12 changed files with 0 additions and 1388 deletions
|
|
@ -1,7 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from .vllm import get_distribution_template # noqa: F401
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
version: 2
|
||||
distribution_spec:
|
||||
description: Use a built-in vLLM engine for running LLM inference
|
||||
providers:
|
||||
inference:
|
||||
- inline::vllm
|
||||
- inline::sentence-transformers
|
||||
vector_io:
|
||||
- inline::faiss
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
safety:
|
||||
- inline::llama-guard
|
||||
agents:
|
||||
- inline::meta-reference
|
||||
telemetry:
|
||||
- inline::meta-reference
|
||||
eval:
|
||||
- inline::meta-reference
|
||||
datasetio:
|
||||
- remote::huggingface
|
||||
- inline::localfs
|
||||
scoring:
|
||||
- inline::basic
|
||||
- inline::llm-as-judge
|
||||
- inline::braintrust
|
||||
tool_runtime:
|
||||
- remote::brave-search
|
||||
- remote::tavily-search
|
||||
- inline::rag-runtime
|
||||
- remote::model-context-protocol
|
||||
image_type: conda
|
||||
additional_pip_packages:
|
||||
- aiosqlite
|
||||
- sqlalchemy[asyncio]
|
||||
|
|
@ -1,132 +0,0 @@
|
|||
version: 2
|
||||
image_name: vllm-gpu
|
||||
apis:
|
||||
- agents
|
||||
- datasetio
|
||||
- eval
|
||||
- inference
|
||||
- safety
|
||||
- scoring
|
||||
- telemetry
|
||||
- tool_runtime
|
||||
- vector_io
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: vllm
|
||||
provider_type: inline::vllm
|
||||
config:
|
||||
tensor_parallel_size: ${env.TENSOR_PARALLEL_SIZE:=1}
|
||||
max_tokens: ${env.MAX_TOKENS:=4096}
|
||||
max_model_len: ${env.MAX_MODEL_LEN:=4096}
|
||||
max_num_seqs: ${env.MAX_NUM_SEQS:=4}
|
||||
enforce_eager: ${env.ENFORCE_EAGER:=False}
|
||||
gpu_memory_utilization: ${env.GPU_MEMORY_UTILIZATION:=0.3}
|
||||
- provider_id: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
config: {}
|
||||
vector_io:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/vllm-gpu}/faiss_store.db
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config:
|
||||
excluded_categories: []
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/vllm-gpu}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/vllm-gpu}/responses_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
||||
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/vllm-gpu}/trace_store.db
|
||||
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/vllm-gpu}/meta_reference_eval.db
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/vllm-gpu}/huggingface_datasetio.db
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/vllm-gpu}/localfs_datasetio.db
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
config: {}
|
||||
- provider_id: llm-as-judge
|
||||
provider_type: inline::llm-as-judge
|
||||
config: {}
|
||||
- provider_id: braintrust
|
||||
provider_type: inline::braintrust
|
||||
config:
|
||||
openai_api_key: ${env.OPENAI_API_KEY:=}
|
||||
tool_runtime:
|
||||
- provider_id: brave-search
|
||||
provider_type: remote::brave-search
|
||||
config:
|
||||
api_key: ${env.BRAVE_SEARCH_API_KEY:=}
|
||||
max_results: 3
|
||||
- provider_id: tavily-search
|
||||
provider_type: remote::tavily-search
|
||||
config:
|
||||
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
|
||||
max_results: 3
|
||||
- provider_id: rag-runtime
|
||||
provider_type: inline::rag-runtime
|
||||
config: {}
|
||||
- provider_id: model-context-protocol
|
||||
provider_type: remote::model-context-protocol
|
||||
config: {}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/vllm-gpu}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/vllm-gpu}/inference_store.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
provider_id: vllm
|
||||
model_type: llm
|
||||
- metadata:
|
||||
embedding_dimension: 384
|
||||
model_id: all-MiniLM-L6-v2
|
||||
provider_id: sentence-transformers
|
||||
model_type: embedding
|
||||
shields: []
|
||||
vector_dbs: []
|
||||
datasets: []
|
||||
scoring_fns: []
|
||||
benchmarks: []
|
||||
tool_groups:
|
||||
- toolgroup_id: builtin::websearch
|
||||
provider_id: tavily-search
|
||||
- toolgroup_id: builtin::rag
|
||||
provider_id: rag-runtime
|
||||
server:
|
||||
port: 8321
|
||||
|
|
@ -1,122 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from llama_stack.apis.models import ModelType
|
||||
from llama_stack.distribution.datatypes import ModelInput, Provider
|
||||
from llama_stack.providers.inline.inference.sentence_transformers import (
|
||||
SentenceTransformersInferenceConfig,
|
||||
)
|
||||
from llama_stack.providers.inline.inference.vllm import VLLMConfig
|
||||
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
|
||||
from llama_stack.templates.template import (
|
||||
DistributionTemplate,
|
||||
RunConfigSettings,
|
||||
ToolGroupInput,
|
||||
)
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["inline::vllm", "inline::sentence-transformers"],
|
||||
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
||||
"safety": ["inline::llama-guard"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
"eval": ["inline::meta-reference"],
|
||||
"datasetio": ["remote::huggingface", "inline::localfs"],
|
||||
"scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
|
||||
"tool_runtime": [
|
||||
"remote::brave-search",
|
||||
"remote::tavily-search",
|
||||
"inline::rag-runtime",
|
||||
"remote::model-context-protocol",
|
||||
],
|
||||
}
|
||||
|
||||
name = "vllm-gpu"
|
||||
inference_provider = Provider(
|
||||
provider_id="vllm",
|
||||
provider_type="inline::vllm",
|
||||
config=VLLMConfig.sample_run_config(),
|
||||
)
|
||||
vector_io_provider = Provider(
|
||||
provider_id="faiss",
|
||||
provider_type="inline::faiss",
|
||||
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
||||
)
|
||||
embedding_provider = Provider(
|
||||
provider_id="sentence-transformers",
|
||||
provider_type="inline::sentence-transformers",
|
||||
config=SentenceTransformersInferenceConfig.sample_run_config(),
|
||||
)
|
||||
|
||||
inference_model = ModelInput(
|
||||
model_id="${env.INFERENCE_MODEL}",
|
||||
provider_id="vllm",
|
||||
)
|
||||
embedding_model = ModelInput(
|
||||
model_id="all-MiniLM-L6-v2",
|
||||
provider_id="sentence-transformers",
|
||||
model_type=ModelType.embedding,
|
||||
metadata={
|
||||
"embedding_dimension": 384,
|
||||
},
|
||||
)
|
||||
default_tool_groups = [
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::websearch",
|
||||
provider_id="tavily-search",
|
||||
),
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::rag",
|
||||
provider_id="rag-runtime",
|
||||
),
|
||||
]
|
||||
|
||||
return DistributionTemplate(
|
||||
name=name,
|
||||
distro_type="self_hosted",
|
||||
description="Use a built-in vLLM engine for running LLM inference",
|
||||
container_image=None,
|
||||
template_path=None,
|
||||
providers=providers,
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider, embedding_provider],
|
||||
"vector_io": [vector_io_provider],
|
||||
},
|
||||
default_models=[inference_model, embedding_model],
|
||||
default_tool_groups=default_tool_groups,
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMA_STACK_PORT": (
|
||||
"8321",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"INFERENCE_MODEL": (
|
||||
"meta-llama/Llama-3.2-3B-Instruct",
|
||||
"Inference model loaded into the vLLM engine",
|
||||
),
|
||||
"TENSOR_PARALLEL_SIZE": (
|
||||
"1",
|
||||
"Number of tensor parallel replicas (number of GPUs to use).",
|
||||
),
|
||||
"MAX_TOKENS": (
|
||||
"4096",
|
||||
"Maximum number of tokens to generate.",
|
||||
),
|
||||
"ENFORCE_EAGER": (
|
||||
"False",
|
||||
"Whether to use eager mode for inference (otherwise cuda graphs are used).",
|
||||
),
|
||||
"GPU_MEMORY_UTILIZATION": (
|
||||
"0.7",
|
||||
"GPU memory utilization for the vLLM engine.",
|
||||
),
|
||||
},
|
||||
)
|
||||
Loading…
Add table
Add a link
Reference in a new issue