vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

all : be more strict about converting float to double (#458)

Browse source 
* Be more strict about converting float to double

* Test equivalence of round, SILU implementations

Test module is commented out in CMakeLists.txt because the tests may
take a long time, depending on how much the compiler optimizes.

* Fix softmax in perplexity.cpp

* all : prefer float over double where appropriate

* perplexity : add <cmath>

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Stephan Walter 2023-03-28 16:48:20 +00:00 • committed by GitHub
parent 20e1e84884
commit 436e561931
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 185 additions and 117 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama.h
View file

@ -45,7 +45,7 @@ extern "C" {
} llama_token_data;
typedef void (*llama_progress_callback)(double progress, void *ctx);
typedef void (*llama_progress_callback)(float progress, void *ctx);
struct llama_context_params {
int n_ctx; // text context
@ -134,9 +134,9 @@ extern "C" {
const llama_token * last_n_tokens_data,
int last_n_tokens_size,
int top_k,
double top_p,
double temp,
double repeat_penalty);
float top_p,
float temp,
float repeat_penalty);
// Performance information
LLAMA_API void llama_print_timings(struct llama_context * ctx);