ggml: add Q1_0 1-bit quantization support (CPU) (#21273)

* ggml: add Q1_0 and Q1_0_g128 1-bit quantization support (CPU)

* add generic fallback for x86

* remove Q1_0 (group size 32)

* rename Q1_0_g128 => Q1_0

* fix Q1_0 LlamaFileType Enum

* Fix trailing spaces; add generic fallback for othre backends

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* fix /r/n spacing + arch-fallback

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

ggml/src/ggml-cpu/quants.c

@@ -22,6 +22,10 @@
 
 #define UNUSED GGML_UNUSED
 
+void quantize_row_q1_0(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k) {
+    quantize_row_q1_0_ref(x, y, k);
+}
+
 void quantize_row_q4_0(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k) {
     quantize_row_q4_0_ref(x, y, k);
 }
@@ -116,6 +120,51 @@ void quantize_row_q8_K_generic(const float * GGML_RESTRICT x, void * GGML_RESTRI
 
 //===================================== Dot products =================================
 
+void ggml_vec_dot_q1_0_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc) {
+    const int qk = QK1_0;
+    const int nb = n / qk;
+
+    assert(n % qk == 0);
+    assert(nrc == 1);
+    UNUSED(nrc);
+    UNUSED(bx);
+    UNUSED(by);
+    UNUSED(bs);
+
+    const block_q1_0 * GGML_RESTRICT x = vx;
+    const block_q8_0 * GGML_RESTRICT y = vy;
+
+    float sumf = 0.0;
+
+    for (int i = 0; i < nb; i++) {
+        const float d0 = GGML_FP16_TO_FP32(x[i].d);
+
+        float sumi = 0.0f;
+
+        for (int k = 0; k < 4; k++) {
+            const float d1 = GGML_FP16_TO_FP32(y[i*4 + k].d);
+
+            int sumi_block = 0;
+
+            for (int j = 0; j < QK8_0; j++) {
+                const int bit_index = k * QK8_0 + j;
+                const int byte_index = bit_index / 8;
+                const int bit_offset = bit_index % 8;
+
+                const int xi = ((x[i].qs[byte_index] >> bit_offset) & 1) ? 1 : -1;
+                sumi_block += xi * y[i*4 + k].qs[j];
+            }
+
+            sumi += d1 * sumi_block;
+        }
+
+        sumf += d0 * sumi;
+    }
+
+    *s = sumf;
+}
+
+
 void ggml_vec_dot_q4_0_q8_0_generic(int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc) {
     const int qk = QK8_0;
     const int nb = n / qk;