Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
35 lines
1.3 KiB
Python
35 lines
1.3 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
import requests
|
|
from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter
|
|
from opentelemetry.sdk.trace import TracerProvider
|
|
from opentelemetry.sdk.trace.export import BatchSpanProcessor, ConsoleSpanExporter
|
|
from opentelemetry.trace import SpanKind, set_tracer_provider
|
|
from opentelemetry.trace.propagation.tracecontext import TraceContextTextMapPropagator
|
|
|
|
trace_provider = TracerProvider()
|
|
set_tracer_provider(trace_provider)
|
|
|
|
trace_provider.add_span_processor(BatchSpanProcessor(OTLPSpanExporter()))
|
|
trace_provider.add_span_processor(BatchSpanProcessor(ConsoleSpanExporter()))
|
|
|
|
tracer = trace_provider.get_tracer("dummy-client")
|
|
|
|
url = "http://localhost:8000/v1/completions"
|
|
with tracer.start_as_current_span("client-span", kind=SpanKind.CLIENT) as span:
|
|
prompt = "San Francisco is a"
|
|
span.set_attribute("prompt", prompt)
|
|
headers = {}
|
|
TraceContextTextMapPropagator().inject(headers)
|
|
payload = {
|
|
"model": "facebook/opt-125m",
|
|
"prompt": prompt,
|
|
"max_tokens": 10,
|
|
"n": 3,
|
|
"use_beam_search": "true",
|
|
"temperature": 0.0,
|
|
# "stream": True,
|
|
}
|
|
response = requests.post(url, headers=headers, json=payload)
|