From: Georgi Gerganov Date: Thu, 20 Apr 2023 17:44:05 +0000 (+0300) Subject: ggml : fix Q4_3 quantization X-Git-Tag: gguf-v0.4.0~913 X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=66aab46079609972ee1f7bd6f319d826205a2fbd;p=pkg%2Fggml%2Fsources%2Fllama.cpp ggml : fix Q4_3 quantization Broke it during conflict resolution in last PR --- diff --git a/ggml.c b/ggml.c index 1aa8ee30..50f114d9 100644 --- a/ggml.c +++ b/ggml.c @@ -12210,6 +12210,12 @@ size_t ggml_quantize_chunk(enum ggml_type type, const float * src, void * dst, i block_q4_2 * block = (block_q4_2*)dst + start / QK4_2; result = ggml_quantize_q4_2(src + start, block, n, n, hist); } break; + case GGML_TYPE_Q4_3: + { + GGML_ASSERT(start % QK4_3 == 0); + block_q4_3 * block = (block_q4_3*)dst + start / QK4_3; + result = ggml_quantize_q4_3(src + start, block, n, n, hist); + } break; default: assert(false); }