Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

metal: add CONV_3D (#19927)

Browse Source 
* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* metal:add conv_3d backend

Rebased with master and resolved conflicts.

* Resolved issues related to changes in variable names

* kernel void kernel_upscale_bilinear_f32 was missing in my branch, added back, should pass all tests now

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Rashid Ul Islam
2026-03-23 09:45:34 +02:00
committed by GitHub
co-authored by Georgi Gerganov
parent 7a0b6a635e
commit 177c75852a
7 changed files with 232 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal.metal
+92
View File
@@ -4883,6 +4883,98 @@ kernel void kernel_upscale_bilinear_f32(
}
}
template <typename T>
kernel void kernel_conv_3d(
constant ggml_metal_kargs_conv_3d & args,
device const char * src0, // Weights [IC * OC, KD, KH, KW]
device const char * src1, // Inputs [IC * N, ID, IH, IW]
device char * dst, // Outputs [OC * N, OD, OH, OW]
uint3 tgpig[[threadgroup_position_in_grid]],
uint3 tpitg[[thread_position_in_threadgroup]]) {
// 1. Un-flatten the spatial dimension from Grid X
int64_t spatial_idx = tgpig.x * 32 + tpitg.x;
if (spatial_idx >= args.OW * args.OH * args.OD) {
return; // Thread falls outside the spatial volume
}
int64_t od = spatial_idx / (args.OW * args.OH);
int64_t oh = (spatial_idx / args.OW) % args.OH;
int64_t ow = spatial_idx % args.OW;
// 2. Map Y to Channels, Z to Batch
int64_t oc = tgpig.y;
int64_t batch_idx = tgpig.z;
// 3. Calculate anchor coordinates in the Input volume
int64_t i_w_base = ow * args.s0 - args.p0;
int64_t i_h_base = oh * args.s1 - args.p1;
int64_t i_d_base = od * args.s2 - args.p2;
float sum = 0.0f;
// 4. Gather Loop (Iterate over Input Channels -> Depth -> Height -> Width)
for (int64_t ic = 0; ic < args.IC; ++ic) {
// ggml packs batch and channel together in the 4th dimension
int64_t src_cn_idx = batch_idx * args.IC + ic;
int64_t w_cn_idx = oc * args.IC + ic;
for (int64_t kz = 0; kz < args.KD; ++kz) {
int64_t id = i_d_base + kz * args.d2;
if (id < 0 || id >= args.ID) continue; // Boundary check (Padding)
for (int64_t ky = 0; ky < args.KH; ++ky) {
int64_t ih = i_h_base + ky * args.d1;
if (ih < 0 || ih >= args.IH) continue;
for (int64_t kx = 0; kx < args.KW; ++kx) {
int64_t iw = i_w_base + kx * args.d0;
if (iw < 0 || iw >= args.IW) continue;
// Convert multi-dimensional coordinates to flat byte offsets
int64_t w_idx = kx*args.nb00 + ky*args.nb01 + kz*args.nb02 + w_cn_idx*args.nb03;
int64_t i_idx = iw*args.nb10 + ih*args.nb11 + id*args.nb12 + src_cn_idx*args.nb13;
// Dereference memory and cast weights to f32 if they were f16
float w_val = (float)*(device const T*)((device const char*)src0 + w_idx);
float i_val = *(device const float*)((device const char*)src1 + i_idx);
sum += w_val * i_val;
}
}
}
}
// 5. Write the accumulated value out to RAM
int64_t dst_cn_idx = batch_idx * args.OC + oc;
int64_t d_idx = ow*args.nb0 + oh*args.nb1 + od*args.nb2 + dst_cn_idx*args.nb3;
*(device float*)(dst + d_idx) = sum;
}
// Explicit instantiations so the JIT compiler can find them by name
template [[host_name("kernel_conv_3d_f32_f32")]]
kernel void kernel_conv_3d<float>(
constant ggml_metal_kargs_conv_3d & args,
device const char * src0,
device const char * src1,
device char * dst,
uint3 tgpig[[threadgroup_position_in_grid]],
uint3 tpitg[[thread_position_in_threadgroup]]);
// Explicit instantiation for f16 weights
template [[host_name("kernel_conv_3d_f16_f32")]]
kernel void kernel_conv_3d<half>(
constant ggml_metal_kargs_conv_3d & args,
device const char * src0,
device const char * src1,
device char * dst,
uint3 tgpig[[threadgroup_position_in_grid]],
uint3 tpitg[[thread_position_in_threadgroup]]);
static inline float bicubic_weight1(float x) {
const float a = -0.75f;
return ((a + 2) * x - (a + 3)) * x * x + 1;