Files
Gahow Wang 445e491123 Add vLLM v0.18.1 source tree with KV transfer abort fix
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>
2026-05-22 00:30:38 +08:00

52 lines
1.5 KiB
Python

# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from vllm import LLM, SamplingParams
from vllm.config import KVTransferConfig
def read_prompts():
"""Read prompts from output.txt"""
prompts = []
try:
with open("output.txt") as f:
for line in f:
prompts.append(line.strip())
print(f"Loaded {len(prompts)} prompts from output.txt")
return prompts
except FileNotFoundError:
print("Error: output.txt file not found")
exit(-1)
def main():
prompts = read_prompts()
sampling_params = SamplingParams(temperature=0, top_p=0.95, max_tokens=10)
llm = LLM(
model="meta-llama/Llama-3.2-1B-Instruct",
enforce_eager=True,
gpu_memory_utilization=0.8,
max_num_batched_tokens=64,
max_num_seqs=16,
kv_transfer_config=KVTransferConfig(
kv_connector="ExampleConnector",
kv_role="kv_both",
kv_connector_extra_config={"shared_storage_path": "local_storage"},
),
) # , max_model_len=2048, max_num_batched_tokens=2048)
# 1ST generation (prefill instance)
outputs = llm.generate(prompts, sampling_params)
print("-" * 30)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}\nGenerated text: {generated_text!r}")
print("-" * 30)
if __name__ == "__main__":
main()