MCPcopy Create free account
hub / github.com/Tiiny-AI/PowerInfer / ggml_quantize_q3_K

Function ggml_quantize_q3_K

ggml-quants.c:1798–1806  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1796}
1797
1798size_t ggml_quantize_q3_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
1799 (void)hist; // TODO: collect histograms
1800
1801 for (int j = 0; j < n; j += k) {
1802 block_q3_K * restrict y = (block_q3_K *)dst + j/QK_K;
1803 quantize_row_q3_K_reference(src + j, y, k);
1804 }
1805 return (n/QK_K*sizeof(block_q3_K));
1806}
1807
1808// ====================== 4-bit (de)-quantization
1809

Callers 1

ggml_quantize_chunkFunction · 0.85

Calls 1

Tested by

no test coverage detected