xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 03:54:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Core] Remove unused prev_sampled_token_ids_invalid_indices input batch field (#26514)

Browse Source 
Signed-off-by: Nick Hill <nhill@redhat.com>
This commit is contained in:
Nick Hill 2025-10-09 13:22:14 -07:00 committed by GitHub
parent 44f633dba1
commit 2e54db4d2b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 0 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/v1/worker/gpu_input_batch.py
View File

@ -251,7 +251,6 @@ class InputBatch:
# Cached reference to the GPU tensor of previously sampled tokens
self.prev_sampled_token_ids: Optional[torch.Tensor] = None
self.prev_sampled_token_ids_invalid_indices: Optional[set[int]] = None
self.prev_req_id_to_index: Optional[dict[str, int]] = None
@property

3
vllm/v1/worker/gpu_model_runner.py
View File

@ -2305,9 +2305,6 @@ class GPUModelRunner(LoRAModelRunnerMixin, KVConnectorModelRunnerMixin):
# These will be copied into input_ids in the next step
# when preparing inputs.
self.input_batch.prev_sampled_token_ids = sampled_token_ids
self.input_batch.prev_sampled_token_ids_invalid_indices = (
invalid_req_indices_set
)
self.input_batch.prev_req_id_to_index = {
req_id: i
for i, req_id in enumerate(self.input_batch.req_ids)