|
ember.cpp 0.1.0
C++ inference engine for Llama-family and paperkiln models (CPU, CUDA, WebAssembly)
|
#include <distributed_coordinator.h>

Public Attributes | |
| std::string | request_id |
| std::string | prompt |
| int | max_tokens |
| float | temperature |
| int | top_k |
| float | top_p |
| std::string | system_prompt |
| int | target_node = -1 |
Definition at line 41 of file distributed_coordinator.h.
| int tinyllama::DistributedCoordinator::InferenceRequest::max_tokens |
Definition at line 44 of file distributed_coordinator.h.
Referenced by tinyllama::DistributedCoordinator::deserialize_request().
| std::string tinyllama::DistributedCoordinator::InferenceRequest::prompt |
Definition at line 43 of file distributed_coordinator.h.
| std::string tinyllama::DistributedCoordinator::InferenceRequest::request_id |
Definition at line 42 of file distributed_coordinator.h.
Referenced by run_interactive_master().
| std::string tinyllama::DistributedCoordinator::InferenceRequest::system_prompt |
Definition at line 48 of file distributed_coordinator.h.
| int tinyllama::DistributedCoordinator::InferenceRequest::target_node = -1 |
Definition at line 49 of file distributed_coordinator.h.
| float tinyllama::DistributedCoordinator::InferenceRequest::temperature |
Definition at line 45 of file distributed_coordinator.h.
| int tinyllama::DistributedCoordinator::InferenceRequest::top_k |
Definition at line 46 of file distributed_coordinator.h.
| float tinyllama::DistributedCoordinator::InferenceRequest::top_p |
Definition at line 47 of file distributed_coordinator.h.