llama-cpp/0.6.0

Inference of LLaMA model in pure C/C++

#ai#llama#llm

Using llama-cpp

Loading usage information…

Packages

Linuxx86_64Release
package IDa8ee8eca4ec8bc0cf57f48f4d061e1681b59ec34
Recipe revisionaae6ed7b508d24635e0ac71802e5a24f
compilergcc
compiler.cppstdgnu17
compiler.version13
optionsshared=True with_cuda=False with_examples=False with_vulkan=False
Linuxx86_64Release
package IDce791d0c608a4aea0089d677dda305d5cc0fdcdf
Recipe revisionaae6ed7b508d24635e0ac71802e5a24f
compilergcc
compiler.cppstdgnu17
compiler.version13
optionsfPIC=True shared=False with_cuda=False with_examples=False with_vulkan=False
Macosarmv8Release
package ID264143fbc97e48529680eb52e870501cf5fca280
Recipe revisionaae6ed7b508d24635e0ac71802e5a24f
compilerapple-clang
compiler.cppstdgnu17
compiler.version17
optionsfPIC=True shared=False with_cuda=False with_examples=False
Macosarmv8Release
package IDe4ad95b57afdc866b2091268de73117407a3f50f
Recipe revisionaae6ed7b508d24635e0ac71802e5a24f
compilerapple-clang
compiler.cppstdgnu17
compiler.version17
optionsshared=True with_cuda=False with_examples=False
Macosx86_64Release
package ID024ff23d17ff3c05d9080bfd00c52d9afdebc301
Recipe revisionaae6ed7b508d24635e0ac71802e5a24f
compilerapple-clang
compiler.cppstdgnu17
compiler.version17
optionsfPIC=True shared=False with_cuda=False with_examples=False
Macosx86_64Release
package ID09225c5e1db2d30e4807f1c4c8cbbd2c3a0ea0cf
Recipe revisionaae6ed7b508d24635e0ac71802e5a24f
compilerapple-clang
compiler.cppstdgnu17
compiler.version17
optionsshared=True with_cuda=False with_examples=False
Windowsx86_64Release
package ID1cbaf925c87b0761af68d47cb9a4a0297a3a49d0
Recipe revisionaae6ed7b508d24635e0ac71802e5a24f
compilermsvc
compiler.cppstd17
compiler.version194
compiler.runtimedynamic
compiler.runtime_typeRelease
optionsshared=False with_cuda=False with_examples=False with_vulkan=False
Windowsx86_64Release
package IDfc51180a4f8bbecd38870153226f46a2ca55da6c
Recipe revisionaae6ed7b508d24635e0ac71802e5a24f
compilermsvc
compiler.cppstd17
compiler.version194
compiler.runtimedynamic
compiler.runtime_typeRelease
optionsshared=True with_cuda=False with_examples=False with_vulkan=False

Dependencies

Loading dependencies…

!◈ MITf24bcfed0bc0763ea84126e5ae28a60a
!◈ MITcf567245c1489d93ae4d19be436e3d1f
!◈ MITf86dfd4ec3c193f53547a659a9de0fed
!◈ MIT0e6b0dec232453bebd3366b3059c00e7
!◈ MIT8d87c34e3d0c44559f03fbe75bf7f211
!◈ MITc5d8251b84afa3f7d5c06ad29b467c11
✓◈ MITaae6ed7b508d24635e0ac71802e5a24f

🔍 Ready to secure your dependencies in seconds?

  1. Register for free at conan.io/audit/register.
  2. Save your token and activate it via the confirmation email you receive.
  3. Configure Conan to use your token:
    conan audit provider auth conancenter --token=<token>
  4. Scan for vulnerabilities:
    # Check a specific reference
    conan audit list llama-cpp/0.6.0
    # Scan the entire dependency graph
    conan audit scan --requires=llama-cpp/0.6.0

Note: For more details on the Conan Audit command, please read this post.

Tip: To avoid exposing your token in shell history, authenticate using an environment variable (e.g. CONAN_AUDIT_PROVIDER_TOKEN_CONANCENTER=<token>). For more info, see the documentation.

conanv0.6.0
[![Conan Center](https://img.shields.io/conan/v/llama-cpp)](https://conan.io/center/recipes/llama-cpp)