Zijie Tian ed3c8bb4b8 🐛 fix: memory leak in XAttentionBSAPolicy select_blocks ...

Fix severe memory leak (64GB -> 4GB growth) by:
- Remove unused sparse_metadata storage (was accumulating attn_scores)
- Delete intermediate tensor list (attn_scores_list) after use
- Explicitly delete intermediate tensors before return

Before: 16GB -> 80GB during 128K prefill
After:  16GB -> 19.8GB during 128K prefill

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-23 09:30:18 +08:00

..

__init__.py

[WIP] Before refactor the nanovllm sparse policy.

2026-01-19 22:34:44 +08:00

full_policy.py

🔧 feat: add density statistics tracking to sparse policies

2026-01-23 08:53:22 +08:00

policy.py

♻️ refactor: move select_blocks from policy to attention layer

2026-01-23 05:21:28 +08:00

quest.py

[WIP] Before add Quest policy.

2026-01-07 02:32:30 +08:00

xattn_bsa.py

🐛 fix: memory leak in XAttentionBSAPolicy select_blocks

2026-01-23 09:30:18 +08:00