parakon-runtime / ggml /src /ggml-virtgpu

175 kB

Ctrl+K

1 contributor

History: 1 commit

kat0012

Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6)

6609e2b verified about 1 month ago

backend
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
include
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
CMakeLists.txt

2.71 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
apir_cs_ggml-rpc-front.cpp

3.51 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-backend-buffer-type.cpp

3.52 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-backend-buffer.cpp

5.44 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-backend-device.cpp

6.13 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-backend-reg.cpp

7.1 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-backend.cpp

2.67 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-remoting.h

2.6 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggmlremoting_functions.yaml

4.39 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
regenerate_remoting.py

13.2 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-apir.h

366 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-forward-backend.cpp

2 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-forward-buffer-type.cpp

3.52 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-forward-buffer.cpp

5.89 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-forward-device.cpp

5.76 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-forward-impl.h

2.87 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-forward.gen.h

3.69 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-shm.cpp

2.74 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-shm.h

423 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-utils.cpp

5.96 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu-utils.h

2.19 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu.cpp

19.3 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
virtgpu.h

3.19 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago