zijie-tian/nano-vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
216 Commits 3 Branches 0 Tags
a239bfb40d2c3320993be3fcd14bee2e2e094d8e
Commit Graph

1 Commits

Author SHA1 Message Date
Zijie Tian
6180055ed8 📝 docs: add chunked attention solutions guide and update doc index 
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>
 2026-01-20 04:48:20 +08:00