mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-16 11:27:03 +00:00
cd5e3b5754
* server : support unified context across slots * cont : fix speculative decoding initialization * context : fix n_ctx_per_seq computation * server : purge slots one by one * tests : add unified cache server tests * llama : update per-seq context computation * test-thread-safety : handle tiny training context of the input model * server : fix server_tokens clear() * server : use 4 slots + unified KV by default * llama : add note about context size queries * cont : update todos [no ci] * context : do not cap the size of the context * tests : adjust parameters to be CI friendlier * context : add warning
43 lines
1.0 KiB
C++
43 lines
1.0 KiB
C++
#pragma once
|
|
|
|
#include "llama.h"
|
|
|
|
#include <cstdint>
|
|
|
|
#define LLAMA_MAX_SEQ 256
|
|
|
|
struct llama_cparams {
|
|
uint32_t n_ctx; // context size used during inference
|
|
uint32_t n_ctx_seq; // context for a single sequence
|
|
uint32_t n_batch;
|
|
uint32_t n_ubatch;
|
|
uint32_t n_seq_max;
|
|
int32_t n_threads; // number of threads to use for generation
|
|
int32_t n_threads_batch; // number of threads to use for batch processing
|
|
|
|
float rope_freq_base;
|
|
float rope_freq_scale;
|
|
|
|
uint32_t n_ctx_orig_yarn;
|
|
// These hyperparameters are not exposed in GGUF, because all
|
|
// existing YaRN models use the same values for them.
|
|
float yarn_ext_factor;
|
|
float yarn_attn_factor;
|
|
float yarn_beta_fast;
|
|
float yarn_beta_slow;
|
|
|
|
bool embeddings;
|
|
bool causal_attn;
|
|
bool offload_kqv;
|
|
bool flash_attn;
|
|
bool no_perf;
|
|
bool warmup;
|
|
bool op_offload;
|
|
bool kv_unified;
|
|
|
|
enum llama_pooling_type pooling_type;
|
|
|
|
ggml_backend_sched_eval_callback cb_eval;
|
|
void * cb_eval_user_data;
|
|
};
|