root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

llama : fix compile warnings

Browse Source
This commit is contained in:
Georgi Gerganov 2023-05-02 23:09:08 +03:00
parent 5d5817ca60
commit 0e6cbff1b7
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
4 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/benchmark/benchmark-matmult.cpp
View File

@ -38,9 +38,9 @@ float tensor_sum_elements(struct ggml_tensor * tensor) {
#define TENSOR_TYPE_AS_STR(TYPE) TYPE == GGML_TYPE_F32 ? "FP32" : TYPE == GGML_TYPE_F16 ? "FP16" : TYPE == GGML_TYPE_Q4_0 ? "Q4_0" : TYPE == GGML_TYPE_Q4_1 ? "Q4_1" : "UNKNOWN" #define TENSOR_TYPE_AS_STR(TYPE) TYPE == GGML_TYPE_F32 ? "FP32" : TYPE == GGML_TYPE_F16 ? "FP16" : TYPE == GGML_TYPE_Q4_0 ? "Q4_0" : TYPE == GGML_TYPE_Q4_1 ? "Q4_1" : "UNKNOWN"
#define TENSOR_DUMP(TENSOR) printf("%15s: type = %i (%5s) ne = %5ld x %5ld x %5ld, nb = (%5li, %5li, %5li) - ", #TENSOR, \ #define TENSOR_DUMP(TENSOR) printf("%15s: type = %i (%5s) ne = %5d x %5d x %5d, nb = (%5li, %5li, %5li) - ", #TENSOR, \
TENSOR->type,TENSOR_TYPE_AS_STR(TENSOR->type),\ TENSOR->type,TENSOR_TYPE_AS_STR(TENSOR->type),\
TENSOR->ne[0], TENSOR->ne[1], TENSOR->ne[2], TENSOR->nb[0], TENSOR->nb[1], TENSOR->nb[2]); \ (int) TENSOR->ne[0], (int) TENSOR->ne[1], (int) TENSOR->ne[2], TENSOR->nb[0], TENSOR->nb[1], TENSOR->nb[2]); \
{ float sum = tensor_sum_elements(TENSOR); printf("Sum of tensor %s is %6.2f\n",#TENSOR, sum); } { float sum = tensor_sum_elements(TENSOR); printf("Sum of tensor %s is %6.2f\n",#TENSOR, sum); }
struct benchmark_params_struct { struct benchmark_params_struct {
@ -138,7 +138,7 @@ int main(int argc, char ** argv) {
ctx = ggml_init(params); ctx = ggml_init(params);
if (!ctx) { if (!ctx) {
fprintf(stderr, "%s: ggml_init() failed\n", __func__); fprintf(stderr, "%s: ggml_init() failed\n", __func__);
return false; return 1;
} }

4
llama.cpp
View File

@ -1702,7 +1702,7 @@ void llama_sample_temperature(struct llama_context * ctx, llama_token_data_array
} }
} }
void llama_sample_repetition_penalty(struct llama_context * ctx, llama_token_data_array * candidates, llama_token * last_tokens, size_t last_tokens_size, float penalty) { void llama_sample_repetition_penalty(struct llama_context * ctx, llama_token_data_array * candidates, const llama_token * last_tokens, size_t last_tokens_size, float penalty) {
if (last_tokens_size == 0 || penalty == 1.0f) { if (last_tokens_size == 0 || penalty == 1.0f) {
return; return;
} }
@ -1731,7 +1731,7 @@ void llama_sample_repetition_penalty(struct llama_context * ctx, llama_token_dat
} }
} }
void llama_sample_frequency_and_presence_penalties(struct llama_context * ctx, llama_token_data_array * candidates, llama_token * last_tokens_p, size_t last_tokens_size, float alpha_frequency, float alpha_presence) { void llama_sample_frequency_and_presence_penalties(struct llama_context * ctx, llama_token_data_array * candidates, const llama_token * last_tokens_p, size_t last_tokens_size, float alpha_frequency, float alpha_presence) {
if (last_tokens_size == 0 || (alpha_frequency == 0.0f && alpha_presence == 0.0f)) { if (last_tokens_size == 0 || (alpha_frequency == 0.0f && alpha_presence == 0.0f)) {
return; return;
} }

4
llama.h
View File

@ -192,10 +192,10 @@ extern "C" {
// Sampling functions // Sampling functions
/// @details Repetition penalty described in CTRL academic paper https://arxiv.org/abs/1909.05858, with negative logit fix. /// @details Repetition penalty described in CTRL academic paper https://arxiv.org/abs/1909.05858, with negative logit fix.
LLAMA_API void llama_sample_repetition_penalty(struct llama_context * ctx, llama_token_data_array * candidates, llama_token * last_tokens, size_t last_tokens_size, float penalty); LLAMA_API void llama_sample_repetition_penalty(struct llama_context * ctx, llama_token_data_array * candidates, const llama_token * last_tokens, size_t last_tokens_size, float penalty);
/// @details Frequency and presence penalties described in OpenAI API https://platform.openai.com/docs/api-reference/parameter-details. /// @details Frequency and presence penalties described in OpenAI API https://platform.openai.com/docs/api-reference/parameter-details.
LLAMA_API void llama_sample_frequency_and_presence_penalties(struct llama_context * ctx, llama_token_data_array * candidates, llama_token * last_tokens, size_t last_tokens_size, float alpha_frequency, float alpha_presence); LLAMA_API void llama_sample_frequency_and_presence_penalties(struct llama_context * ctx, llama_token_data_array * candidates, const llama_token * last_tokens, size_t last_tokens_size, float alpha_frequency, float alpha_presence);
/// @details Sorts candidate tokens by their logits in descending order and calculate probabilities based on logits. /// @details Sorts candidate tokens by their logits in descending order and calculate probabilities based on logits.
LLAMA_API void llama_sample_softmax(struct llama_context * ctx, llama_token_data_array * candidates); LLAMA_API void llama_sample_softmax(struct llama_context * ctx, llama_token_data_array * candidates);

4
tests/test-sampling.cpp
View File

@ -131,7 +131,7 @@ void test_repetition_penalty(
llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false }; llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };
llama_sample_softmax(nullptr, &candidates_p); llama_sample_softmax(nullptr, &candidates_p);
DUMP(&candidates_p); DUMP(&candidates_p);
llama_sample_repetition_penalty(nullptr, &candidates_p, (llama_token *)last_tokens.data(), last_tokens.size(), penalty); llama_sample_repetition_penalty(nullptr, &candidates_p, (const llama_token *) last_tokens.data(), last_tokens.size(), penalty);
llama_sample_softmax(nullptr, &candidates_p); llama_sample_softmax(nullptr, &candidates_p);
DUMP(&candidates_p); DUMP(&candidates_p);
@ -160,7 +160,7 @@ void test_frequency_presence_penalty(
llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false }; llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };
llama_sample_softmax(nullptr, &candidates_p); llama_sample_softmax(nullptr, &candidates_p);
// DUMP(&candidates_p); // DUMP(&candidates_p);
llama_sample_frequency_and_presence_penalties(nullptr, &candidates_p, (llama_token *)last_tokens.data(), last_tokens.size(), alpha_frequency, alpha_presence); llama_sample_frequency_and_presence_penalties(nullptr, &candidates_p, (const llama_token *) last_tokens.data(), last_tokens.size(), alpha_frequency, alpha_presence);
llama_sample_softmax(nullptr, &candidates_p); llama_sample_softmax(nullptr, &candidates_p);
// DUMP(&candidates_p); // DUMP(&candidates_p);