text-generation-inference
5ce89059
- feat(server): pre-allocate past key values for flash causal LM (#412)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
feat(server): pre-allocate past key values for flash causal LM (#412)
References
#412 - feat(server): pre-allocate past key values for flash causal LM
Author
OlivierDehaene
Parents
ca650e5b
Loading