MCPcopy Create free account
hub / github.com/Tiiny-AI/PowerInfer / ggml_quantize_q6_K

Function ggml_quantize_q6_K

ggml-quants.c:2316–2325  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

2314}
2315
2316size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist) {
2317 assert(k % QK_K == 0);
2318 (void)hist; // TODO: collect histograms
2319
2320 for (int j = 0; j < n; j += k) {
2321 block_q6_K * restrict y = (block_q6_K *)dst + j/QK_K;
2322 quantize_row_q6_K_reference(src + j, y, k);
2323 }
2324 return (n/QK_K*sizeof(block_q6_K));
2325}
2326
2327//===================================== Q8_K ==============================================
2328

Callers 1

ggml_quantize_chunkFunction · 0.85

Calls 1

Tested by

no test coverage detected