21.2 MB

Ctrl+K

1 contributor

History: 4 commits

kat0012

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

6609e2b verified about 1 month ago

ggml-blas
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-cann
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-cpu
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-cuda
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 4) about 1 month ago
ggml-et
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 4) about 1 month ago
ggml-hexagon
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 4) about 1 month ago
ggml-hip
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 4) about 1 month ago
ggml-metal
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 5) about 1 month ago
ggml-musa
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 5) about 1 month ago
ggml-opencl
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 5) about 1 month ago
ggml-openvino
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 5) about 1 month ago
ggml-rpc
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 5) about 1 month ago
ggml-sycl
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-virtgpu
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-vulkan
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-webgpu
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-zdnn
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-zendnn
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
CMakeLists.txt

27 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-alloc.c

47.8 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-backend-dl.cpp

1.05 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-backend-dl.h

791 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-backend-impl.h

14.8 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-backend-meta.cpp

119 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-backend-reg.cpp

18.6 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-backend.cpp

99.1 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-common.h

136 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 3) about 1 month ago
ggml-feats.h

4.89 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 4) about 1 month ago
ggml-impl.h

25.8 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 4) about 1 month ago
ggml-opt.cpp

42.1 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 5) about 1 month ago
ggml-quants.c

230 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 5) about 1 month ago
ggml-quants.h

10 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 5) about 1 month ago
ggml-threading.cpp

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

198 Bytes
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
ggml-version.h.in

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

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

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

58.1 kB
Parakon runtime: llama.cpp fork with fused 1-bit CUDA/Metal/CPU kernels (part 6) about 1 month ago
parakon_iq1_grids.h

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