xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-07-19 12:47:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix overflow indexing in causal_conv1d kernel (#20938)

Browse Source 
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
This commit is contained in:
Thomas Parnell 2025-07-14 23:43:07 +02:00 committed by GitHub
parent 149f2435a5
commit 86f3ac21ce
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/layers/mamba/ops/causal_conv1d.py
View File

@ -92,7 +92,8 @@ def _causal_conv1d_fwd_kernel( # continuous batching
if IS_CONTINUOUS_BATCHING: if IS_CONTINUOUS_BATCHING:
# cache_idx # cache_idx
conv_state_batch_coord = tl.load(conv_state_indices_ptr + idx_seq) conv_state_batch_coord = tl.load(conv_state_indices_ptr + idx_seq).to(
tl.int64)
else: else:
# cache_idx # cache_idx
conv_state_batch_coord = idx_seq conv_state_batch_coord = idx_seq