MCPcopy Create free account
hub / github.com/abetlen/llama-cpp-python / llama_n_batch

Function llama_n_batch

llama_cpp/llama_cpp.py:1608–1608  ·  view source on GitHub ↗
(ctx: llama_context_p, /)

Source from the content-addressed store, hash-verified

1606# LLAMA_API uint32_t llama_n_batch (const struct llama_context * ctx);
1607@ctypes_function("llama_n_batch", [llama_context_p_ctypes], ctypes.c_uint32)
1608def llama_n_batch(ctx: llama_context_p, /) -> int: ...
1609
1610
1611# LLAMA_API uint32_t llama_n_ubatch (const struct llama_context * ctx);

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected

Used in the wild real call sites across dependent graphs

searching dependent graphs…