Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Tiiny-AI/PowerInfer
/ llama_n_batch
Function
llama_n_batch
smallthinker/src/llama-context.cpp:2273–2275 ·
view source on GitHub ↗
Source
from the content-addressed store, hash-verified
2271
}
2272
2273
uint32_t llama_n_batch(const llama_context * ctx) {
2274
return ctx->n_batch();
2275
}
2276
2277
uint32_t llama_n_ubatch(const llama_context * ctx) {
2278
return ctx->n_ubatch();
Callers
8
init
Method · 0.85
update_slots
Method · 0.85
process_chunk
Method · 0.85
common_speculative_init
Function · 0.85
main
Function · 0.85
main
Function · 0.85
encode
Function · 0.85
generate
Function · 0.85
Calls
1
n_batch
Method · 0.80
Tested by
3
common_speculative_init
Function · 0.68
main
Function · 0.68
main
Function · 0.68