vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 18:09:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/server.yml
#	CMakeLists.txt
#	Makefile
#	examples/embedding/embedding.cpp
#	examples/imatrix/imatrix.cpp
#	examples/llama-bench/llama-bench.cpp
#	examples/llava/MobileVLM-README.md
#	examples/parallel/parallel.cpp
#	examples/perplexity/perplexity.cpp
#	examples/quantize/CMakeLists.txt
#	examples/server/README.md
#	examples/speculative/speculative.cpp
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo 2024-09-13 16:17:24 +08:00
commit e44ddf26ef
47 changed files with 117978 additions and 117646 deletions
Download patch file Download diff file Expand all files Collapse all files

32
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
@ -1058,6 +1058,9 @@ extern "C" {
LLAMA_API struct llama_sampler * llama_sampler_chain_get(const struct llama_sampler * chain, int32_t i);
LLAMA_API int llama_sampler_chain_n (const struct llama_sampler * chain);
// after removing a sampler, the chain will no longer own it, and it will not be freed when the chain is freed
LLAMA_API struct llama_sampler * llama_sampler_chain_remove( struct llama_sampler * chain, int32_t i);
// available samplers:
LLAMA_API struct llama_sampler * llama_sampler_init_greedy (void);
@ -1175,13 +1178,30 @@ 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);