[ROCm][CI] Solidify entrypoint LLM lifecycle (#51280)

Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Andreas Karatzas
2026-08-13 12:24:02 -05:00
committed by GitHub
parent 69d4c3a06b
commit b96bcd0b47
24 changed files with 1002 additions and 1103 deletions
+25 -12
View File
@@ -1,10 +1,10 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
from vllm import LLM, SamplingParams
from vllm import SamplingParams
def test_gpu_memory_utilization():
def test_gpu_memory_utilization(vllm_runner):
prompts = [
"Hello, my name is",
"The president of the United States is",
@@ -15,13 +15,26 @@ def test_gpu_memory_utilization():
# makes sure gpu_memory_utilization is per-instance limit,
# not a global limit
llms = [
LLM(model="facebook/opt-125m", gpu_memory_utilization=0.3, enforce_eager=True)
for i in range(3)
]
for llm in llms:
outputs = llm.generate(prompts, sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
with (
vllm_runner(
"facebook/opt-125m",
gpu_memory_utilization=0.3,
enforce_eager=True,
) as runner_0,
vllm_runner(
"facebook/opt-125m",
gpu_memory_utilization=0.3,
enforce_eager=True,
) as runner_1,
vllm_runner(
"facebook/opt-125m",
gpu_memory_utilization=0.3,
enforce_eager=True,
) as runner_2,
):
for runner in (runner_0, runner_1, runner_2):
outputs = runner.llm.generate(prompts, sampling_params)
for output in outputs:
prompt = output.prompt
generated_text = output.outputs[0].text
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")