llama.cpp
06230cb8
- allows the usage of 4-10 gpus for stepfun and laguna in tensor parallel (#24554)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
25 days ago
allows the usage of 4-10 gpus for stepfun and laguna in tensor parallel (#24554)
References
#24554 - Fix 24486: TP: allows the usage of 4-10 gpus for stepfun and laguna
Author
krampenschiesser
Parents
5c311426
Loading