Skip to content

[None][chore] Use a cached model path for Ray integration test #8660

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+14 −2
Open

[None][chore] Use a cached model path for Ray integration test #8660

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 12 additions & 1 deletion examples/ray_orchestrator/llm_inference_async_ray.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,19 +1,30 @@
# Generate text asynchronously with Ray orchestrator.
import argparse
import asyncio

from tensorrt_llm import LLM, SamplingParams
from tensorrt_llm.llmapi import KvCacheConfig


def main():
parser = argparse.ArgumentParser(
description="Generate text asynchronously with Ray orchestrator.")
parser.add_argument(
"--model",
type=str,
default="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
help=
"HuggingFace model name or path to local HF model (default: TinyLlama/TinyLlama-1.1B-Chat-v1.0)"
)
args = parser.parse_args()
# Configure KV cache memory usage fraction.
kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.5,
max_tokens=4096,
enable_block_reuse=True)

# model could accept HF model name or a path to local HF model.
llm = LLM(
model="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
model=args.model,
kv_cache_config=kv_cache_config,
max_seq_len=1024,
max_batch_size=1,
Expand Down
3 changes: 2 additions & 1 deletion tests/integration/defs/examples/test_ray.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@ def ray_example_root(llm_root):

def test_llm_inference_async_ray(ray_example_root, llm_venv):
script_path = os.path.join(ray_example_root, "llm_inference_async_ray.py")
venv_check_call(llm_venv, [script_path])
model_path = f"{llm_models_root()}/llama-models-v2/TinyLlama-1.1B-Chat-v1.0"
venv_check_call(llm_venv, [script_path, "--model", model_path])


@pytest.mark.skip_less_device(2)
Expand Down