xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-17 04:47:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

minor

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon 2025-08-28 13:19:10 -07:00
parent 19c0dfc469
commit 405578121c
1 changed files with 1 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/v1/worker/gpu_model_runner.py
View File

@ -559,10 +559,8 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
# batch_idx -> req_id
req_ids = sorted(scheduler_output.num_scheduled_tokens,
key=scheduler_output.num_scheduled_tokens.get)
# req_id -> batch_idx
req_id_to_batch_idx = {req_id: i for i, req_id in enumerate(req_ids)}
# batch_idx -> req_idx
idx_mapping_list = [
self.requests.req_id_to_index[req_id] for req_id in req_ids
@ -633,7 +631,7 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
if draft_token_ids:
num_draft_tokens[i] = len(draft_token_ids)
spec_decode_metadata = self._calc_spec_decode_metadata(
num_draft_tokens, self.query_start_loc_np[1:num_reqs + 1])
num_draft_tokens, self.query_start_loc.np[1:num_reqs + 1])
logits_indices = spec_decode_metadata.logits_indices
logits_indices_padded = None