mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-24 13:19:54 +00:00
add more distro templates (#279)
* verify dockers * together distro verified * readme * fireworks distro * fireworks compose up * fireworks verified
This commit is contained in:
parent
cf27d19dd5
commit
4d2bd2d39e
18 changed files with 265 additions and 42 deletions
|
@ -6,28 +6,7 @@ services:
|
|||
- $HOME/.cache/huggingface:/data
|
||||
ports:
|
||||
- "5009:5009"
|
||||
devices:
|
||||
- nvidia.com/gpu=all
|
||||
environment:
|
||||
- CUDA_VISIBLE_DEVICES=0
|
||||
- HF_HOME=/data
|
||||
- HF_DATASETS_CACHE=/data
|
||||
- HF_MODULES_CACHE=/data
|
||||
- HF_HUB_CACHE=/data
|
||||
command: ["--dtype", "bfloat16", "--usage-stats", "on", "--sharded", "false", "--model-id", "meta-llama/Llama-3.1-8B-Instruct", "--port", "5009", "--cuda-memory-fraction", "0.3"]
|
||||
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
|
||||
healthcheck:
|
||||
test: ["CMD", "curl", "-f", "http://text-generation-inference:5009/health"]
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue