~ruther/guix-local

d8a63bbcee616f224c10462dbfb117ec009c50d8 — John Fremlin 2 years ago 227dee6
gnu: llama-cpp: Use OpenBLAS.

For faster prompt processing, OpenBLAS is recommended by
https://github.com/ggerganov/llama.cpp

* gnu/packages/machine-learning.scm (llama-cpp)[arguments]: Add
 #:configure-flags.
[native-inputs]: Add pkg-config.
[propagated-inputs]: Add openblas.

Change-Id: Iaf6f22252da13e2d6f503992878b35b0da7de0aa
Signed-off-by: Christopher Baines <mail@cbaines.net>
1 files changed, 4 insertions(+), 1 deletions(-)

M gnu/packages/machine-learning.scm
M gnu/packages/machine-learning.scm => gnu/packages/machine-learning.scm +4 -1
@@ 541,6 541,8 @@ Performance is achieved by using the LLVM JIT compiler.")
      (build-system cmake-build-system)
      (arguments
       (list
        #:configure-flags
        '(list "-DLLAMA_BLAS=ON" "-DLLAMA_BLAS_VENDOR=OpenBLAS")
        #:modules '((ice-9 textual-ports)
                    (guix build utils)
                    ((guix build python-build-system) #:prefix python:)


@@ 575,8 577,9 @@ Performance is achieved by using the LLVM JIT compiler.")
              (lambda _
                (copy-file "bin/main" (string-append #$output "/bin/llama")))))))
      (inputs (list python))
      (native-inputs (list pkg-config))
      (propagated-inputs
       (list python-numpy python-pytorch python-sentencepiece))
       (list python-numpy python-pytorch python-sentencepiece openblas))
      (home-page "https://github.com/ggerganov/llama.cpp")
      (synopsis "Port of Facebook's LLaMA model in C/C++")
      (description "This package provides a port to Facebook's LLaMA collection