Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/appdevforall/CodeOnTheGo
/ llama_n_batch
Function
llama_n_batch
subprojects/llama.cpp/src/llama-context.cpp:3072–3074 ·
view source on GitHub ↗
Source
from the content-addressed store, hash-verified
3070
}
3071
3072
uint32_t llama_n_batch(const llama_context * ctx) {
3073
return ctx->n_batch();
3074
}
3075
3076
uint32_t llama_n_ubatch(const llama_context * ctx) {
3077
return ctx->n_ubatch();
Callers
4
load_model
Method · 0.85
update_slots
Method · 0.85
process_chunk
Method · 0.85
common_speculative_state_draft
Method · 0.85
Calls
1
n_batch
Method · 0.80
Tested by
1
common_speculative_state_draft
Method · 0.68