CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : llama_perf + option to disable timings during decode (#9355)

Browse Source 
* llama : llama_perf + option to disable timings during decode

ggml-ci

* common : add llama_arg

* Update src/llama.cpp

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>

* perf : separate functions in the API

ggml-ci

* perf : safer pointer handling + naming update

ggml-ci

* minor : better local var name

* perf : abort on invalid sampler pointer

ggml-ci

---------

Co-authored-by: Xuan Son Nguyen <thichthat@gmail.com>
This commit is contained in:
Georgi Gerganov
2024-09-13 09:53:38 +03:00
committed by GitHub
parent bd35cb0ae3
commit 0abc6a2c25
23 changed files with 135 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
include/llama.h
View File

@@ -343,7 +343,7 @@ extern "C" {
bool embeddings; // if true, extract embeddings (together with logits)
bool offload_kqv; // whether to offload the KQV ops (including the KV cache) to GPU
bool flash_attn; // whether to use flash attention [EXPERIMENTAL]
//bool no_perf; // whether to measure performance timings, TODO: implement
bool no_perf; // whether to measure performance timings
// Abort callback
// if it returns true, execution of llama_decode() will be aborted
@@ -1176,13 +1176,30 @@ extern "C" {
// NOTE: Used by llama.cpp examples, avoid using in third-party apps. Instead, do your own performance measurements.
//
enum llama_perf_type {
LLAMA_PERF_TYPE_CONTEXT = 0,
LLAMA_PERF_TYPE_SAMPLER_CHAIN = 1,
struct llama_perf_context_data {
double t_start_ms;
double t_load_ms;
double t_p_eval_ms;
double t_eval_ms;
int32_t n_p_eval;
int32_t n_eval;
};
LLAMA_API void llama_perf_print(const void * ctx, enum llama_perf_type type);
LLAMA_API void llama_perf_reset( void * ctx, enum llama_perf_type type);
struct llama_perf_sampler_data {
double t_sample_ms;
int32_t n_sample;
};
LLAMA_API struct llama_perf_context_data llama_perf_context (const struct llama_context * ctx);
LLAMA_API void llama_perf_context_print(const struct llama_context * ctx);
LLAMA_API void llama_perf_context_reset( struct llama_context * ctx);
// NOTE: the following work only with samplers constructed via llama_sampler_chain_init
LLAMA_API struct llama_perf_sampler_data llama_perf_sampler (const struct llama_sampler * chain);
LLAMA_API void llama_perf_sampler_print(const struct llama_sampler * chain);
LLAMA_API void llama_perf_sampler_reset( struct llama_sampler * chain);
LLAMA_API void llama_perf_dump_yaml(FILE * stream, const struct llama_context * ctx);