Skip to content
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

Jump to bottom

Fix rpd benchmark script #219

Closed
wants to merge 3 commits into from
Closed

Fix rpd benchmark script #219

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5d7fd4d
fix rpd benchmark script
charlifu Oct 2, 2024
46b2c97
fix naming
charlifu Oct 2, 2024
0ddef16
Merge branch 'main' into fix_rpd_benchmark_latency
gshtras Oct 3, 2024
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
8 changes: 4 additions & 4 deletions benchmarks/profiling/benchmark_latency.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@

from vllm import LLM, SamplingParams
from vllm.engine.arg_utils import DEVICE_OPTIONS, EngineArgs
from vllm.inputs import PromptType
from vllm.inputs import PromptInputs
from vllm.model_executor.layers.quantization import QUANTIZATION_METHODS
from vllm.utils import FlexibleArgumentParser

Expand Down Expand Up @@ -100,19 +100,19 @@ def get_profiling_context(profile_dir: Optional[str] = None,
dummy_prompt_token_ids = np.random.randint(10000,
size=(args.batch_size,
args.input_len))
dummy_prompts: List[PromptType] = [{
dummy_inputs: List[PromptInputs] = [{
"prompt_token_ids": batch
} for batch in dummy_prompt_token_ids.tolist()]

def run_to_completion(profile_dir: Optional[str] = None):
if profile_dir:
with get_profiling_context():
llm.generate(dummy_prompts,
llm.generate(dummy_inputs,
sampling_params=sampling_params,
use_tqdm=False)
else:
start_time = time.perf_counter()
llm.generate(dummy_prompts,
llm.generate(dummy_inputs,
sampling_params=sampling_params,
use_tqdm=False)
end_time = time.perf_counter()
Expand Down
Loading