xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-16 11:16:45 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix][TPU] Use np array when updating cache slot_mapping (#17971)

Browse Source 
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
This commit is contained in:
Siyuan Liu 2025-05-11 21:58:33 -07:00 committed by GitHub
parent 19a3c78d1f
commit 430783018c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/worker/tpu_model_runner.py
View File

@ -531,7 +531,7 @@ class TPUModelRunner(LoRAModelRunnerMixin):
np.add(block_numbers * self.block_size,
block_offsets,
out=self.input_batch.block_table.
slot_mapping_cpu[:total_num_scheduled_tokens])
slot_mapping_np[:total_num_scheduled_tokens])
# Prepare the attention metadata.
self.query_start_loc_np[0] = 0