holm/whisper.cpp
1
1
Fork 0
forked from extern/whisper.cpp
Code Issues Pull Requests Packages Projects Releases Wiki Activity

sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)

Browse Source 
* sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.)

* metal : allow env metal variable to override resource path (#1415)

* Allow env variable to override resource path

* Update ggml-metal.m

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* sync : restore common / main from `master`

* sync : restore whisper from `master`

* talk-llama : update to latest llama.cpp

* ruby : fix build

* ggml : fix 32-bit ARM build

* ggml : fix MIN / MAX macro collisions + update ios bindings

* ggml : fix ifdefs and MIN / MAX again

* exampels : fix Obj-C and Swift examples

* ggml : fix 32-bit ARM compatibility

* ggml : one more attempt to fix 32-bit ARM compat

* whisper : fix support for larger graphs

---------

Co-authored-by: Chris Raethke <codesoda@users.noreply.github.com>
This commit is contained in:
Georgi Gerganov
2023-11-03 21:35:05 +02:00
committed by GitHub
parent 8a2bee6717
commit f96e1c5b78
38 changed files with 30875 additions and 7843 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
examples/common.h
View File

@ -17,10 +17,15 @@
//
struct gpt_params {
int32_t seed = -1; // RNG seed
int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
int32_t n_predict = 200; // new tokens to predict
int32_t n_batch = 8; // batch size for prompt processing
int32_t seed = -1; // RNG seed
int32_t n_threads = std::min(4, (int32_t) std::thread::hardware_concurrency());
int32_t n_predict = 200; // new tokens to predict
int32_t n_parallel = 1; // number of parallel streams
int32_t n_batch = 8; // batch size for prompt processing
int32_t n_ctx = 2048; // context size (this is the KV cache max size)
int32_t n_gpu_layers = 0; // number of layers to offlload to the GPU
bool ignore_eos = false; // ignore EOS token when generating text
// sampling parameters
int32_t top_k = 40;
@ -35,8 +40,6 @@ struct gpt_params {
bool interactive = false;
int32_t interactive_port = -1;
int32_t n_gpu_layers = 0;
};
bool gpt_params_parse(int argc, char ** argv, gpt_params & params);