Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/antirez/llama.cpp-deepseek-v4-flash
/ n_ubatch
Method
n_ubatch
src/llama-context.cpp:706–708 ·
view source on GitHub ↗
Source
from the content-addressed store, hash-verified
704
}
705
706
uint32_t llama_context::n_ubatch() const {
707
return cparams.n_ubatch;
708
}
709
710
uint32_t llama_context::n_seq_max() const {
711
return cparams.n_seq_max;
Callers
3
opt_init
Method · 0.95
opt_epoch_iter
Method · 0.95
llama_n_ubatch
Function · 0.80
Calls
no outgoing calls
Tested by
no test coverage detected