transformers
4af901d5
- [docs] continuous batching (offloading behavior, max batch tokens, block size minimum) (#46925)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 days ago
[docs] continuous batching (offloading behavior, max batch tokens, block size minimum) (#46925) * docs * block size * prefill batch size
References
#46925 - [docs] continuous batching (offloading behavior, max batch tokens, block size minimum)
Author
stevhliu
Parents
1d828044
Loading