summaryrefslogtreecommitdiff
path: root/ggml/src/iqk/iqk_quantize.h
diff options
context:
space:
mode:
Diffstat (limited to 'ggml/src/iqk/iqk_quantize.h')
-rw-r--r--ggml/src/iqk/iqk_quantize.h8
1 files changed, 8 insertions, 0 deletions
diff --git a/ggml/src/iqk/iqk_quantize.h b/ggml/src/iqk/iqk_quantize.h
index 76fbac3b..d447705b 100644
--- a/ggml/src/iqk/iqk_quantize.h
+++ b/ggml/src/iqk/iqk_quantize.h
@@ -248,6 +248,14 @@ bool iqk_modify_tensor(struct ggml_tensor * tensor);
// So we can re-pack Microsoft's BitNet I2_S quants
void dequantize_row_ms_i2s(const void * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+typedef void (*to_float_t) (const void * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k);
+typedef void (*from_float_t)(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k);
+void iqk_quantize_any(int from_type, int to_type,
+ int64_t ne0, int64_t ne1, int64_t ne2, int64_t ne3,
+ uint64_t nb0, uint64_t nb1, uint64_t nb2, uint64_t nb3,
+ const void * GGML_RESTRICT x, void * GGML_RESTRICT y, void * work_buffer,
+ to_float_t to_float, from_float_t from_float, int ith, int nth);
+
#ifdef __cplusplus
}
#endif