@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 5ecf3e0aaf
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 02:00 UTC

Misc: allow to use proxy in `HTTPConnection` (#12042)

Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>

Yuan committed Jan 15, 2025 at 21:16 UTC 5ecf3e0aafc3ae0e2923e0635adc6b26788429a3
1 file changed +1 -1
vllm/connections.py
+1 -1
@@ -29,7 +29,7 @@ class HTTPConnection:
29 # required, so that the client is only accessible inside async event loop
30 async def get_async_client(self) -> aiohttp.ClientSession:
31 if self._async_client is None or not self.reuse_client:
32 - self._async_client = aiohttp.ClientSession()
32 + self._async_client = aiohttp.ClientSession(trust_env=True)
33
34 return self._async_client
35