mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 30 Packages Projects Releases Wiki Activity

ggml-webgpu: add the upscale shader (#22419)

Browse Source 
* shader(upscale): add the upscale shader with nearest, bilinear and bicubic implementations

* shader(upscale): use macro
This commit is contained in:
Chen Yuan
2026-05-01 01:22:18 -04:00
committed by GitHub
parent a95a11e5b8
commit aab68217b7
3 changed files with 383 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/ggml-webgpu.cpp
+49
View File
@@ -2824,6 +2824,49 @@ static bool ggml_webgpu_can_fuse_rms_norm_mul(const struct ggml_cgraph * cgraph,
return true;
}
static webgpu_encoded_op ggml_webgpu_upscale(webgpu_context ctx, ggml_tensor * src, ggml_tensor * dst) {
const uint32_t mode_flags = (uint32_t) ggml_get_op_params_i32(dst, 0);
std::vector<uint32_t> params = { (uint32_t) (ggml_webgpu_tensor_misalignment(ctx, src) / ggml_type_size(src->type)),
(uint32_t) (ggml_webgpu_tensor_misalignment(ctx, dst) / ggml_type_size(dst->type)),
(uint32_t) (src->nb[0] / ggml_type_size(src->type)),
(uint32_t) (src->nb[1] / ggml_type_size(src->type)),
(uint32_t) (src->nb[2] / ggml_type_size(src->type)),
(uint32_t) (src->nb[3] / ggml_type_size(src->type)),
(uint32_t) (dst->nb[0] / ggml_type_size(dst->type)),
(uint32_t) (dst->nb[1] / ggml_type_size(dst->type)),
(uint32_t) (dst->nb[2] / ggml_type_size(dst->type)),
(uint32_t) (dst->nb[3] / ggml_type_size(dst->type)),
(uint32_t) src->ne[0],
(uint32_t) src->ne[1],
(uint32_t) src->ne[2],
(uint32_t) src->ne[3],
(uint32_t) dst->ne[0],
(uint32_t) dst->ne[1],
(uint32_t) dst->ne[2],
(uint32_t) dst->ne[3],
mode_flags };
std::vector<wgpu::BindGroupEntry> entries = { ggml_webgpu_make_tensor_bind_group_entry(ctx, 0, src),
ggml_webgpu_make_tensor_bind_group_entry(ctx, 1, dst) };
ggml_webgpu_shader_lib_context shader_lib_ctx = {};
shader_lib_ctx.src0 = src;
shader_lib_ctx.dst = dst;
shader_lib_ctx.max_wg_size = ctx->global_ctx->capabilities.limits.maxComputeInvocationsPerWorkgroup;
webgpu_pipeline pipeline = ctx->shader_lib->get_upscale_pipeline(shader_lib_ctx);
auto * decisions = static_cast<ggml_webgpu_generic_shader_decisions *>(pipeline.context.get());
uint32_t total_wg = CEIL_DIV((uint32_t) ggml_nelements(dst), decisions->wg_size);
uint32_t wg_x = std::min(ctx->global_ctx->capabilities.limits.maxComputeWorkgroupsPerDimension, total_wg);
uint32_t wg_y = CEIL_DIV(total_wg, wg_x);
return ggml_backend_webgpu_build(ctx, pipeline, params, entries, wg_x, wg_y);
}
// Returns the encoded command, or std::nullopt if the operation is a no-op
static std::optional<webgpu_encoded_op> ggml_webgpu_encode(webgpu_context ctx,
ggml_cgraph * cgraph,
@@ -2931,6 +2974,8 @@ static std::optional<webgpu_encoded_op> ggml_webgpu_encode(webgpu_context ctx,
return ggml_webgpu_conv_2d(ctx, src0, src1, node);
case GGML_OP_IM2COL:
return ggml_webgpu_im2col(ctx, src0, src1, node);
case GGML_OP_UPSCALE:
return ggml_webgpu_upscale(ctx, src0, node);
default:
return std::nullopt;
}
@@ -4163,6 +4208,10 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const
case GGML_OP_SUM_ROWS:
supports_op = op->type == GGML_TYPE_F32 && src0->type == op->type && ggml_is_contiguous_rows(src0);
break;
case GGML_OP_UPSCALE:
supports_op = (op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16) &&
(src0->type == GGML_TYPE_F32 || src0->type == GGML_TYPE_F16);
break;
default:
break;
}