aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGeorgi Gerganov <ggerganov@gmail.com>2023-05-02 23:09:08 +0300
committerGeorgi Gerganov <ggerganov@gmail.com>2023-05-02 23:09:08 +0300
commit0e6cbff1b7509628c588e661166f6e187137734d (patch)
tree3f1431d95cf186ea1b2d7afee0722d02e6ef2658
parent5d5817ca603d4cb451bed26594aa3dcd93f4ec56 (diff)
llama : fix compile warnings
-rw-r--r--examples/benchmark/benchmark-matmult.cpp6
-rw-r--r--llama.cpp4
-rw-r--r--llama.h4
-rw-r--r--tests/test-sampling.cpp4
4 files changed, 9 insertions, 9 deletions
diff --git a/examples/benchmark/benchmark-matmult.cpp b/examples/benchmark/benchmark-matmult.cpp
index 2cc1a14..6117ae3 100644
--- a/examples/benchmark/benchmark-matmult.cpp
+++ b/examples/benchmark/benchmark-matmult.cpp
@@ -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_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->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); }
struct benchmark_params_struct {
@@ -138,7 +138,7 @@ int main(int argc, char ** argv) {
ctx = ggml_init(params);
if (!ctx) {
fprintf(stderr, "%s: ggml_init() failed\n", __func__);
- return false;
+ return 1;
}
diff --git a/llama.cpp b/llama.cpp
index a8156bc..d4ef056 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -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) {
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)) {
return;
}
diff --git a/llama.h b/llama.h
index 4052a8c..81f4317 100644
--- a/llama.h
+++ b/llama.h
@@ -192,10 +192,10 @@ extern "C" {
// Sampling functions
/// @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.
- 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.
LLAMA_API void llama_sample_softmax(struct llama_context * ctx, llama_token_data_array * candidates);
diff --git a/tests/test-sampling.cpp b/tests/test-sampling.cpp
index 7eee4f6..8ce59af 100644
--- a/tests/test-sampling.cpp
+++ b/tests/test-sampling.cpp
@@ -131,7 +131,7 @@ void test_repetition_penalty(
llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };
llama_sample_softmax(nullptr, &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);
DUMP(&candidates_p);
@@ -160,7 +160,7 @@ void test_frequency_presence_penalty(
llama_token_data_array candidates_p = { candidates.data(), candidates.size(), false };
llama_sample_softmax(nullptr, &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);
// DUMP(&candidates_p);