Skip to content

GitLab

Unverified Commit 86f3ac21 authored by Thomas Parnell's avatar Thomas Parnell Committed by GitHub
Browse files

Fix overflow indexing in causal_conv1d kernel (#20938) 


Signed-off-by: default avatarThomas Parnell <tpa@zurich.ibm.com>
parent 149f2435
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 1 deletion
vllm/model_executor/layers/mamba/ops/causal_conv1d.py
View file @ 86f3ac21
...@@ -92,7 +92,8 @@ def _causal_conv1d_fwd_kernel( # continuous batching ...@@ -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
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment