[Disagg] Support large batch size in proxy server and update NixlConnector doc for DP (#28782)
Signed-off-by: Ming Yang <minos.future@gmail.com>
This commit is contained in:
@@ -30,7 +30,14 @@ async def lifespan(app: FastAPI):
|
||||
prefiller_base_url = f"http://{host}:{port}/v1"
|
||||
app.state.prefill_clients.append(
|
||||
{
|
||||
"client": httpx.AsyncClient(timeout=None, base_url=prefiller_base_url),
|
||||
"client": httpx.AsyncClient(
|
||||
timeout=None,
|
||||
base_url=prefiller_base_url,
|
||||
limits=httpx.Limits(
|
||||
max_connections=None,
|
||||
max_keepalive_connections=None,
|
||||
),
|
||||
),
|
||||
"host": host,
|
||||
"port": port,
|
||||
"id": i,
|
||||
@@ -42,7 +49,14 @@ async def lifespan(app: FastAPI):
|
||||
decoder_base_url = f"http://{host}:{port}/v1"
|
||||
app.state.decode_clients.append(
|
||||
{
|
||||
"client": httpx.AsyncClient(timeout=None, base_url=decoder_base_url),
|
||||
"client": httpx.AsyncClient(
|
||||
timeout=None,
|
||||
base_url=decoder_base_url,
|
||||
limits=httpx.Limits(
|
||||
max_connections=None,
|
||||
max_keepalive_connections=None,
|
||||
),
|
||||
),
|
||||
"host": host,
|
||||
"port": port,
|
||||
"id": i,
|
||||
@@ -169,6 +183,10 @@ async def send_request_to_service(
|
||||
)
|
||||
response.raise_for_status()
|
||||
|
||||
# read/consume the response body to release the connection
|
||||
# otherwise, it would http.ReadError
|
||||
await response.aread()
|
||||
|
||||
return response
|
||||
|
||||
|
||||
@@ -206,6 +224,7 @@ async def _handle_completions(api: str, request: Request):
|
||||
|
||||
# Extract the needed fields
|
||||
response_json = response.json()
|
||||
await response.aclose() # CRITICAL: Release connection back to pool
|
||||
kv_transfer_params = response_json.get("kv_transfer_params", {})
|
||||
if kv_transfer_params:
|
||||
req_data["kv_transfer_params"] = kv_transfer_params
|
||||
|
||||
Reference in New Issue
Block a user