From 77a73403ca8eaced2590559d0f9cebd2b3649d32 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 18 Apr 2023 23:54:57 +0300 Subject: ggml : add new Q4_2 quantization (ARM only) (#1046) * ggml : Q4_2 ARM * ggml : add ggml_is_quantized() * llama : update llama_type_name() with Q4_2 entry * ggml : speed-up q4_2 - 4 threads: ~100ms -> ~90ms - 8 threads: ~55ms -> ~50ms * ggml : optimize q4_2 using vmlaq_n_f32 + vmulq_n_f32 --- examples/quantize/quantize.cpp | 1 + 1 file changed, 1 insertion(+) (limited to 'examples/quantize') diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 5c9e2ad..59cb674 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -14,6 +14,7 @@ int main(int argc, char ** argv) { fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\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); return 1; } -- cgit v1.2.3