Something went wrong. Try again.
llama.cpp fork for Ternary Bonsai 2 27B: MTP speculation, suffix cache reuse (SCR), q8 KV, two-slot fairness, fused DeltaNet kernels
Something went wrong. Try again.
1.5 kB · 59 lines
C++
at main
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960#include "llama-memory.h"
llama_memory_status llama_memory_status_combine(llama_memory_status s0, llama_memory_status s1) { bool has_update = false;
switch (s0) { case LLAMA_MEMORY_STATUS_SUCCESS: { has_update = true; break; } case LLAMA_MEMORY_STATUS_NO_UPDATE: { break; } case LLAMA_MEMORY_STATUS_FAILED_PREPARE: case LLAMA_MEMORY_STATUS_FAILED_COMPUTE: { return s0; } }
switch (s1) { case LLAMA_MEMORY_STATUS_SUCCESS: { has_update = true; break; } case LLAMA_MEMORY_STATUS_NO_UPDATE: { break; } case LLAMA_MEMORY_STATUS_FAILED_PREPARE: case LLAMA_MEMORY_STATUS_FAILED_COMPUTE: { return s1; } }
// if either status has an update, then the combined status has an update return has_update ? LLAMA_MEMORY_STATUS_SUCCESS : LLAMA_MEMORY_STATUS_NO_UPDATE;}
bool llama_memory_status_is_fail(llama_memory_status status) { switch (status) { case LLAMA_MEMORY_STATUS_SUCCESS: case LLAMA_MEMORY_STATUS_NO_UPDATE: { return false; } case LLAMA_MEMORY_STATUS_FAILED_PREPARE: case LLAMA_MEMORY_STATUS_FAILED_COMPUTE: { return true; } }
return false;}