update dequant

ggerganov · Mar 12, 2024 · 4f74b87 · 4f74b87
1 parent 835622b
commit 4f74b87
Showing 1 changed file with 7 additions and 7 deletions.
diff --git a/ggml-sycl.cpp b/ggml-sycl.cpp
@@ -4902,14 +4902,14 @@ static void dequantize_block_iq1_s(const void * __restrict__ vx, dst_t * __restr
  const int il = tid/8; // 0...3
  const int ib = tid%8; // 0...7
  dst_t * y = yy + i*QK_K + 32*ib + 8*il;
- const uint8_t * qs = x[i].qs + 8*ib;
- const uint8_t * grid1 = (const uint8_t *)(iq1s_grid + qs[2*il+0]);
- const uint8_t * grid2 = (const uint8_t *)(iq1s_grid + qs[2*il+1]);
- const float d = (float)x[i].d * (2*((x[i].qh[ib] >> 12) & 0xf) + 1);
- const uint8_t signs = ksigns_iq2xs[(x[i].qh[ib] >> 3*il) & 7];
+ const float delta = x[i].qh[ib] & 0x8000 ? -1 - IQ1S_DELTA : -1 + IQ1S_DELTA;
+ const float d = (float)x[i].d * (2*((x[i].qh[ib] >> 12) & 7) + 1);
+ uint32_t grid32[2]; const int8_t * q = (const int8_t *)grid32;
+ grid32[0] = iq1s_grid_gpu[x[i].qs[4*ib+il] | (((x[i].qh[ib] >> 3*il) & 7) << 8)];
+ grid32[1] = (grid32[0] >> 4) & 0x0f0f0f0f;
+ grid32[0] &= 0x0f0f0f0f;
  for (int j = 0; j < 4; ++j) {
- y[j+0] = d * grid1[j] * (signs & kmask_iq2xs[j+0] ? -1.f : 1.f);
- y[j+4] = d * grid2[j] * (signs & kmask_iq2xs[j+4] ? -1.f : 1.f);
+ y[j] = d * (q[j] + delta);
  }
 #else
  assert(false);