llama.cpp
Add support for QRWKV6 hybrid models & slight optimization for RWKV6
#11001
Merged
Overview
Commits
12
Changes
View On GitHub
  • File
    README.md
  • File
    convert_hf_to_gguf.py
  • ggml
    • include
      • File
        ggml.h
    • src
      • ggml-cpu
        • File
          ggml-cpu.c
      • ggml-cuda
        • File
          ggml-cuda.cu
        • File
          gla.cu
        • File
          gla.cuh
        • File
          wkv6.cu
      • ggml-sycl
        • File
          wkv6.cpp
      • ggml-vulkan
        • File
          ggml-vulkan.cpp
      • File
        ggml.c
  • gguf-py/gguf
    • File
      constants.py
    • File
      gguf_writer.py
    • File
      tensor_mapping.py
  • src
    • File
      llama-arch.cpp
    • File
      llama-arch.h
    • File
      llama-hparams.cpp
    • File
      llama-hparams.h
    • File
      llama-model.cpp
    • File
      llama-model.h
    • File
      llama-quant.cpp
    • File
      llama.cpp
  • tests
    • File
      test-backend-ops.cpp

Loading comments...

FAQ Terms Privacy Refunds Impressum