📝 docs: add chunked attention solutions guide and update doc index

Browse Source

Add comprehensive documentation analyzing the 32K chunked offload
accuracy issues with proposed solutions covering LSE precision,
ring buffer state management, and position encoding validation.

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

...

This commit is contained in:

Zijie Tian

2026-01-20 04:48:20 +08:00

parent 4cbd451af7

commit 6180055ed8

2 changed files with 1080 additions and 1 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

1078

docs/chunked_attention_solutions.md Normal file

File diff suppressed because it is too large Load Diff