西风逍遥游 859845bbb4 Merge branch 'dev' into codex/test-suite-representative-tests

2026-09-11 14:25:00 +08:00

..

AffineQuant.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

AffineQuant.h

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

AffineQuantInternal.h

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

CpuKernels.cpp

tensor: AITemplate-style compile pipeline, gpgpu Sequence, mini-LLM demo and weight-only quantization

2026-08-18 17:42:38 +08:00

CpuKernels.h

tensor: AITemplate-style compile pipeline, gpgpu Sequence, mini-LLM demo and weight-only quantization

2026-08-18 17:42:38 +08:00

GpuBackend.cpp

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

GpuBackend.h

feat: zeroerr parameter validation + Doxygen API documentation

2026-08-19 09:01:12 +08:00

Graph.cpp

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

Graph.h

feat: zeroerr parameter validation + Doxygen API documentation

2026-08-19 09:01:12 +08:00

GraphStorage.cpp

feat(agent): add evolutionary learning with Squirrel and tensor GPU backends

2026-09-10 16:46:56 +08:00

KernelGen.cpp

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

KernelGen.h

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

KernelGenInternal.h

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

KernelGenResize.cpp

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

KernelGenWgsl.cpp

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

KernelGenWgsl.h

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

KernelGenWgslBindings.cpp

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

KernelGenWgslIndex.cpp

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

KernelGenWgslInternal.h

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

KernelGenWgslReduction.cpp

fix: validate representative tests across native GPU backends

2026-09-11 14:19:51 +08:00

OnnxByteStorage.h

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxCompiler.h

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxCompute.h

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxExecute.cpp

fix(tensor): make ONNX index conversions MSVC warning-clean

2026-09-10 21:12:15 +08:00

OnnxGpgpu.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxGpuKernels.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxGpuKernels.h

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxIndexOps.cpp

fix(tensor): make ONNX index conversions MSVC warning-clean

2026-09-10 21:12:15 +08:00

OnnxInternal.h

fix(tensor): make ONNX index conversions MSVC warning-clean

2026-09-10 21:12:15 +08:00

OnnxLstm.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxMisc.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxModel.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxModel.h

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxNeural.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxNumeric.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxQuant.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxReader.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxRuntime.cpp

fix(tensor): make ONNX index conversions MSVC warning-clean

2026-09-10 21:12:15 +08:00

OnnxShapeOps.cpp

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

OnnxStorage.h

feat(tensor): add quantized ONNX inference with reusable Vulkan sessions

2026-09-10 20:01:21 +08:00

Optimizer.cpp

tensor: AITemplate-style compile pipeline, gpgpu Sequence, mini-LLM demo and weight-only quantization

2026-08-18 17:42:38 +08:00

Optimizer.h

tensor: AITemplate-style compile pipeline, gpgpu Sequence, mini-LLM demo and weight-only quantization

2026-08-18 17:42:38 +08:00

Quant.h

tensor: AITemplate-style compile pipeline, gpgpu Sequence, mini-LLM demo and weight-only quantization

2026-08-18 17:42:38 +08:00

Tensor.cpp

tensor: AITemplate-style compile pipeline, gpgpu Sequence, mini-LLM demo and weight-only quantization

2026-08-18 17:42:38 +08:00

Tensor.h

feat: zeroerr parameter validation + Doxygen API documentation

2026-08-19 09:01:12 +08:00

TF.cpp

tensor: AITemplate-style compile pipeline, gpgpu Sequence, mini-LLM demo and weight-only quantization

2026-08-18 17:42:38 +08:00

TF.h

feat: zeroerr parameter validation + Doxygen API documentation

2026-08-19 09:01:12 +08:00