Skip to content

[Perf] Optimize Preparing Inputs for GPU Model Runner #16484

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

Merged
merged 3 commits into from
Apr 12, 2025
Merged

[Perf] Optimize Preparing Inputs for GPU Model Runner #16484

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7018c25
Optimize prepare inputs for GPU model runner
SnowCharmQ Apr 11, 2025
d150bd3
Format code
SnowCharmQ Apr 11, 2025
ef6fdea
Improve readability
SnowCharmQ Apr 11, 2025
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
12 changes: 4 additions & 8 deletions vllm/v1/worker/gpu_model_runner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -484,14 +484,10 @@ def _prepare_inputs(
self.input_batch.block_table.commit(num_reqs)

# Get the number of scheduled tokens for each request.
# TODO: The Python loop can be slow. Optimize.
num_scheduled_tokens = np.empty(num_reqs, dtype=np.int32)
max_num_scheduled_tokens = 0
for i, req_id in enumerate(self.input_batch.req_ids):
num_tokens = scheduler_output.num_scheduled_tokens[req_id]
num_scheduled_tokens[i] = num_tokens
max_num_scheduled_tokens = max(max_num_scheduled_tokens,
num_tokens)
req_ids = self.input_batch.req_ids
tokens = [scheduler_output.num_scheduled_tokens[i] for i in req_ids]
num_scheduled_tokens = np.array(tokens, dtype=np.int32)
max_num_scheduled_tokens = max(tokens)

# Get request indices.
# E.g., [2, 5, 3] -> [0, 0, 1, 1, 1, 1, 1, 2, 2, 2]
Expand Down