phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-07 12:47:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

base: 35 RPS; safety, 75 RPS

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-09-02 14:00:23 -07:00
parent faf891b40c
commit c3fa3e6333
5 changed files with 41 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -362,7 +362,9 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
return AsyncOpenAI(
base_url=self.config.url,
api_key=self.config.api_token,
http_client=httpx.AsyncClient(verify=self.config.tls_verify),
http_client=httpx.AsyncClient(
verify=self.config.tls_verify, limits=httpx.Limits(max_connections=1000, max_keepalive_connections=1000)
),
)
async def completion(