llama.cpp
bafa0420
- server : enable packing for d1-2B and d1-Omni-2B models (#32553)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
6 hours ago
server : enable packing for d1-2B and d1-Omni-2B models (#32553) * llama-bench : size the batch to the prompt for models without memory Assisted-by: Claude Opus 5.5 * server : read up to 16 lfm3-d1 questions in one pass Assisted-by: Claude Opus 5.5
References
#32553 - server : enable packing for d1-2B and d1-Omni-2B models
Author
tdakhran
Parents
2cbfc3cf
Loading