phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

safety, chore: async inference store write

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-09-03 06:06:02 -07:00
parent faf891b40c
commit d0626ac535
2 changed files with 10 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

8
docs/source/distributions/k8s-benchmark/stack_run_config.yaml
View file

@ -3,6 +3,7 @@ image_name: kubernetes-benchmark-demo
apis: apis:
- agents - agents
- inference - inference
- safety
- telemetry - telemetry
- tool_runtime - tool_runtime
- vector_io - vector_io
@ -30,6 +31,11 @@ providers:
db: ${env.POSTGRES_DB:=llamastack} db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack} user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack} password: ${env.POSTGRES_PASSWORD:=llamastack}
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config:
excluded_categories: []
agents: agents:
- provider_id: meta-reference - provider_id: meta-reference
provider_type: inline::meta-reference provider_type: inline::meta-reference
@ -95,6 +101,8 @@ models:
- model_id: ${env.INFERENCE_MODEL} - model_id: ${env.INFERENCE_MODEL}
provider_id: vllm-inference provider_id: vllm-inference
model_type: llm model_type: llm
shields:
- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
vector_dbs: [] vector_dbs: []
datasets: [] datasets: []
scoring_fns: [] scoring_fns: []

4
llama_stack/core/routers/inference.py
View file

@ -527,7 +527,7 @@ class InferenceRouter(Inference):
# Store the response with the ID that will be returned to the client # Store the response with the ID that will be returned to the client
if self.store: if self.store:
await self.store.store_chat_completion(response, messages) asyncio.create_task(self.store.store_chat_completion(response, messages))
if self.telemetry: if self.telemetry:
metrics = self._construct_metrics( metrics = self._construct_metrics(
@ -855,4 +855,4 @@ class InferenceRouter(Inference):
object="chat.completion", object="chat.completion",
) )
logger.debug(f"InferenceRouter.completion_response: {final_response}") logger.debug(f"InferenceRouter.completion_response: {final_response}")
await self.store.store_chat_completion(final_response, messages) asyncio.create_task(self.store.store_chat_completion(final_response, messages))