llama : multi-threaded quantization (#1075)

* Multi-threading quantization.

Not much gain for simple quantizations, bit it will be important
for quantizations that require more CPU cycles.

* Multi-threading for quantize-stats

It now does the job in ~14 seconds on my Mac for
Q4_0, Q4_1 and Q4_2. Single-threaded it was taking
more than 2 minutes after adding the more elaborate
version of Q4_2.

* Reviewer comments

* Avoiding compiler confusion

After changing chunk_size to const int as suggested by
@ggerganov, clang and GCC starting to warn me that I don't
need to capture it in the lambda. So, I removed it from the
capture list. But that makes the MSVC build fail. So,
making it a constexpr to make every compiler happy.

* Still fighting with lambda captures in MSVC

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

1 files changed, 4 insertions, 3 deletions

diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp
index 49a33a8..5b4812c 100644
--- a/examples/quantize/quantize.cpp
+++ b/examples/quantize/quantize.cpp
@@ -10,8 +10,8 @@
 int main(int argc, char ** argv) {
     ggml_time_init();
 
-    if (argc != 4) {
-        fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
+    if (argc < 4) {
+        fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type [nthread]\n", argv[0]);
         fprintf(stderr, "  type = %d - q4_0\n", LLAMA_FTYPE_MOSTLY_Q4_0);
         fprintf(stderr, "  type = %d - q4_1\n", LLAMA_FTYPE_MOSTLY_Q4_1);
         fprintf(stderr, "  type = %d - q4_2\n", LLAMA_FTYPE_MOSTLY_Q4_2);
@@ -30,6 +30,7 @@ int main(int argc, char ** argv) {
     const std::string fname_out = argv[2];
 
     const enum llama_ftype ftype = (enum llama_ftype)atoi(argv[3]);
+    int nthread = argc > 4 ? atoi(argv[4]) : 0;
 
     const int64_t t_main_start_us = ggml_time_us();
 
@@ -39,7 +40,7 @@ int main(int argc, char ** argv) {
     {
         const int64_t t_start_us = ggml_time_us();
 
-        if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), ftype)) {
+        if (llama_model_quantize(fname_inp.c_str(), fname_out.c_str(), ftype, nthread)) {
             fprintf(stderr, "%s: failed to quantize model from '%s'\n", __func__, fname_inp.c_str());
             return 1;
         }