Distributions updates (slight updates to ollama, add inline-vllm and remote-vllm) (#408)

* remote vllm distro

* add inline-vllm details, fix things

* Write some docs
This commit is contained in:
Ashwin Bharambe 2024-11-08 18:09:39 -08:00 committed by GitHub
parent ba82021d4b
commit 4986e46188
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 365 additions and 46 deletions

View file

@ -0,0 +1 @@
../../llama_stack/templates/inline-vllm/build.yaml

View file

@ -0,0 +1,35 @@
services:
llamastack:
image: llamastack/distribution-inline-vllm
network_mode: "host"
volumes:
- ~/.llama:/root/.llama
- ./run.yaml:/root/my-run.yaml
ports:
- "5000:5000"
devices:
- nvidia.com/gpu=all
environment:
- CUDA_VISIBLE_DEVICES=0
command: []
deploy:
resources:
reservations:
devices:
- driver: nvidia
# that's the closest analogue to --gpus; provide
# an integer amount of devices or 'all'
count: 1
# Devices are reserved using a list of capabilities, making
# capabilities the only required field. A device MUST
# satisfy all the requested capabilities for a successful
# reservation.
capabilities: [gpu]
runtime: nvidia
entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
deploy:
restart_policy:
condition: on-failure
delay: 3s
max_attempts: 5
window: 60s

View file

@ -0,0 +1,66 @@
version: '2'
built_at: '2024-10-08T17:40:45.325529'
image_name: local
docker_image: null
conda_env: local
apis:
- shields
- agents
- models
- memory
- memory_banks
- inference
- safety
providers:
inference:
- provider_id: vllm-inference
provider_type: inline::vllm
config:
model: Llama3.2-3B-Instruct
tensor_parallel_size: 1
gpu_memory_utilization: 0.4
enforce_eager: true
max_tokens: 4096
- provider_id: vllm-safety
provider_type: inline::vllm
config:
model: Llama-Guard-3-1B
tensor_parallel_size: 1
gpu_memory_utilization: 0.2
enforce_eager: true
max_tokens: 4096
safety:
- provider_id: meta0
provider_type: meta-reference
config:
llama_guard_shield:
model: Llama-Guard-3-1B
excluded_categories: []
# Uncomment to use prompt guard
# prompt_guard_shield:
# model: Prompt-Guard-86M
memory:
- provider_id: meta0
provider_type: meta-reference
config: {}
# Uncomment to use pgvector
# - provider_id: pgvector
# provider_type: remote::pgvector
# config:
# host: 127.0.0.1
# port: 5432
# db: postgres
# user: postgres
# password: mysecretpassword
agents:
- provider_id: meta0
provider_type: meta-reference
config:
persistence_store:
namespace: null
type: sqlite
db_path: ~/.llama/runtime/agents_store.db
telemetry:
- provider_id: meta0
provider_type: meta-reference
config: {}