Skip to content

[https://nvbugs/5467548][fix] DeepSeek illegal memory access. #7298

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 29, 2025
Merged

[https://nvbugs/5467548][fix] DeepSeek illegal memory access. #7298

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
31d7c46
Fill 0 to block_ids_per_seq and kv_block_ids_per_seq.
bobboli Aug 27, 2025
9905f2f
Fill 0 for kv_block_ids_per_seq and block_ids_per_seq at prepare, not…
bobboli Aug 28, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions tensorrt_llm/_torch/attention_backend/trtllm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -707,6 +707,7 @@ def get_empty_like(like_tensor: torch.Tensor,
cache_name="block_ids_per_seq",
dtype=torch.int32,
)
self.block_ids_per_seq.fill_(0)
self.kv_block_ids_per_seq = get_empty(
[
self.kv_cache_manager.max_batch_size,
Expand All @@ -715,6 +716,7 @@ def get_empty_like(like_tensor: torch.Tensor,
cache_name="kv_block_ids_per_seq",
dtype=torch.int32,
)
self.kv_block_ids_per_seq.fill_(0)
if self.enable_paged_context_mla:
# for kv cache reuse/chunked context in MLA
self.ctx_cached_token_indptr = get_empty(
Expand Down