René's URL Explorer Experiment


Title: GitHub - albertjin/llama.cpp: LLM inference in C/C++ · GitHub

Open Graph Title: GitHub - albertjin/llama.cpp: LLM inference in C/C++

X Title: GitHub - albertjin/llama.cpp: LLM inference in C/C++

Description: LLM inference in C/C++. Contribute to albertjin/llama.cpp development by creating an account on GitHub.

Open Graph Description: LLM inference in C/C++. Contribute to albertjin/llama.cpp development by creating an account on GitHub.

X Description: LLM inference in C/C++. Contribute to albertjin/llama.cpp development by creating an account on GitHub.

Opengraph URL: https://github.com/albertjin/llama.cpp

X: @github

direct link

Domain: github.com

route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:350b9be8-90d3-5aa5-f373-2f5a1bc6b4c3
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-idAED2:418ED:BADF79:103C95D:6A4E8300
html-safe-nonced23fdca2f0791b3a8f45ad52c30b5871f51e690bfa24162363cf6e4de357dde0
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJBRUQyOjQxOEVEOkJBREY3OToxMDNDOTVEOjZBNEU4MzAwIiwidmlzaXRvcl9pZCI6Ijg0NDU4NTg0MTY4OTU2MjM5MzYiLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmac850998ccb9cb6e174c3cc44fc4c6eaf6fc770ec96d8be2cf3367123facd03dbf
hovercard-subject-tagrepository:796306097
github-keyboard-shortcutsrepository,copilot
google-site-verificationApib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-urlhttps://collector.github.com/github/collect
analytics-location//
fb:app_id1401488693436528
apple-itunes-appapp-id=1477376905, app-argument=https://github.com/albertjin/llama.cpp
twitter:imagehttps://opengraph.githubassets.com/4fbb37dc368b70815b9a9d97e8bc9d9ecaabb8e16390589093757d86fbacbf7c/albertjin/llama.cpp
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/4fbb37dc368b70815b9a9d97e8bc9d9ecaabb8e16390589093757d86fbacbf7c/albertjin/llama.cpp
og:image:altLLM inference in C/C++. Contribute to albertjin/llama.cpp development by creating an account on GitHub.
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
None41b6ab3ba6d20a71766ac245b5a4a94c6fc672a9cd4da7d44c1b33ab8bf6a21c
turbo-cache-controlno-cache
go-importgithub.com/albertjin/llama.cpp git https://github.com/albertjin/llama.cpp.git
octolytics-dimension-user_id640151
octolytics-dimension-user_loginalbertjin
octolytics-dimension-repository_id796306097
octolytics-dimension-repository_nwoalbertjin/llama.cpp
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forktrue
octolytics-dimension-repository_parent_id612354784
octolytics-dimension-repository_parent_nwoggml-org/llama.cpp
octolytics-dimension-repository_network_root_id612354784
octolytics-dimension-repository_network_root_nwoggml-org/llama.cpp
turbo-body-classeslogged-out env-production page-responsive
disable-turbofalse
browser-stats-urlhttps://api.github.com/_private/browser/stats
browser-errors-urlhttps://api.github.com/_private/browser/errors
releasee6a744804e8e70f97b4d5a18a94dcc63db22f97a
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://github.com/albertjin/llama.cpp#start-of-content
https://github.com/
Sign in https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Falbertjin%2Fllama.cpp
GitHub CopilotWrite better code with AIhttps://github.com/features/copilot
GitHub Copilot appDirect agents from issue to mergehttps://github.com/features/ai/github-app
MCP RegistryNewIntegrate external toolshttps://github.com/mcp
ActionsAutomate any workflowhttps://github.com/features/actions
CodespacesInstant dev environmentshttps://github.com/features/codespaces
IssuesPlan and track workhttps://github.com/features/issues
Code ReviewManage code changeshttps://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilitieshttps://github.com/security/advanced-security
Code securitySecure your code as you buildhttps://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they starthttps://github.com/security/advanced-security/secret-protection
Why GitHubhttps://github.com/why-github
Documentationhttps://docs.github.com
Bloghttps://github.blog
Changeloghttps://github.blog/changelog
Marketplacehttps://github.com/marketplace
View all featureshttps://github.com/features
Enterpriseshttps://github.com/enterprise
Small and medium teamshttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
App Modernizationhttps://github.com/solutions/use-case/app-modernization
DevSecOpshttps://github.com/solutions/use-case/devsecops
DevOpshttps://github.com/solutions/use-case/devops
CI/CDhttps://github.com/solutions/use-case/ci-cd
View all use caseshttps://github.com/solutions/use-case
Healthcarehttps://github.com/solutions/industry/healthcare
Financial serviceshttps://github.com/solutions/industry/financial-services
Manufacturinghttps://github.com/solutions/industry/manufacturing
Governmenthttps://github.com/solutions/industry/government
View all industrieshttps://github.com/solutions/industry
View all solutionshttps://github.com/solutions
AIhttps://github.com/resources/articles?topic=ai
Software Developmenthttps://github.com/resources/articles?topic=software-development
DevOpshttps://github.com/resources/articles?topic=devops
Securityhttps://github.com/resources/articles?topic=security
View all topicshttps://github.com/resources/articles
Customer storieshttps://github.com/customer-stories
Events & webinarshttps://github.com/resources/events
Ebooks & reportshttps://github.com/resources/whitepapers
Business insightshttps://github.com/solutions/executive-insights
GitHub Skillshttps://skills.github.com
Documentationhttps://docs.github.com
Customer supporthttps://support.github.com
Community forumhttps://github.com/orgs/community/discussions
Trust centerhttps://github.com/trust-center
Partnershttps://github.com/partners
View all resourceshttps://github.com/resources
GitHub SponsorsFund open source developershttps://github.com/open-source/sponsors
Security Labhttps://securitylab.github.com
Maintainer Communityhttps://maintainers.github.com
Acceleratorhttps://github.com/open-source/accelerator
GitHub Starshttps://stars.github.com
Archive Programhttps://archiveprogram.github.com
Topicshttps://github.com/topics
Trendinghttps://github.com/trending
Collectionshttps://github.com/collections
Enterprise platformAI-powered developer platformhttps://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security featureshttps://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI featureshttps://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 supporthttps://github.com/enterprise/premium-support
Pricinghttps://github.com/pricing
Search syntax tipshttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentationhttps://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Falbertjin%2Fllama.cpp
Sign up https://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=albertjin%2Fllama.cpp
Reloadhttps://github.com/albertjin/llama.cpp
Reloadhttps://github.com/albertjin/llama.cpp
Reloadhttps://github.com/albertjin/llama.cpp
albertjin https://github.com/albertjin
llama.cpphttps://github.com/albertjin/llama.cpp
ggml-org/llama.cpphttps://github.com/ggml-org/llama.cpp
Notifications https://github.com/login?return_to=%2Falbertjin%2Fllama.cpp
Fork 0 https://github.com/login?return_to=%2Falbertjin%2Fllama.cpp
Star 0 https://github.com/login?return_to=%2Falbertjin%2Fllama.cpp
Code https://github.com/albertjin/llama.cpp
Pull requests 0 https://github.com/albertjin/llama.cpp/pulls
Actions https://github.com/albertjin/llama.cpp/actions
Projects https://github.com/albertjin/llama.cpp/projects
Security and quality 0 https://github.com/albertjin/llama.cpp/security
Insights https://github.com/albertjin/llama.cpp/pulse
Code https://github.com/albertjin/llama.cpp
Pull requests https://github.com/albertjin/llama.cpp/pulls
Actions https://github.com/albertjin/llama.cpp/actions
Projects https://github.com/albertjin/llama.cpp/projects
Security and quality https://github.com/albertjin/llama.cpp/security
Insights https://github.com/albertjin/llama.cpp/pulse
https://github.com/albertjin/llama.cpp
Brancheshttps://github.com/albertjin/llama.cpp/branches
Tagshttps://github.com/albertjin/llama.cpp/tags
https://github.com/albertjin/llama.cpp/branches
https://github.com/albertjin/llama.cpp/tags
2,796 Commitshttps://github.com/albertjin/llama.cpp/commits/master/
https://github.com/albertjin/llama.cpp/commits/master/
.devopshttps://github.com/albertjin/llama.cpp/tree/master/.devops
.devopshttps://github.com/albertjin/llama.cpp/tree/master/.devops
.githubhttps://github.com/albertjin/llama.cpp/tree/master/.github
.githubhttps://github.com/albertjin/llama.cpp/tree/master/.github
cihttps://github.com/albertjin/llama.cpp/tree/master/ci
cihttps://github.com/albertjin/llama.cpp/tree/master/ci
cmakehttps://github.com/albertjin/llama.cpp/tree/master/cmake
cmakehttps://github.com/albertjin/llama.cpp/tree/master/cmake
commonhttps://github.com/albertjin/llama.cpp/tree/master/common
commonhttps://github.com/albertjin/llama.cpp/tree/master/common
docshttps://github.com/albertjin/llama.cpp/tree/master/docs
docshttps://github.com/albertjin/llama.cpp/tree/master/docs
exampleshttps://github.com/albertjin/llama.cpp/tree/master/examples
exampleshttps://github.com/albertjin/llama.cpp/tree/master/examples
ggml-cudahttps://github.com/albertjin/llama.cpp/tree/master/ggml-cuda
ggml-cudahttps://github.com/albertjin/llama.cpp/tree/master/ggml-cuda
gguf-pyhttps://github.com/albertjin/llama.cpp/tree/master/gguf-py
gguf-pyhttps://github.com/albertjin/llama.cpp/tree/master/gguf-py
grammarshttps://github.com/albertjin/llama.cpp/tree/master/grammars
grammarshttps://github.com/albertjin/llama.cpp/tree/master/grammars
kompute @ 4565194https://github.com/nomic-ai/kompute/tree/4565194ed7c32d1d2efa32ceab4d3c6cae006306
kompute @ 4565194https://github.com/nomic-ai/kompute/tree/4565194ed7c32d1d2efa32ceab4d3c6cae006306
kompute-shadershttps://github.com/albertjin/llama.cpp/tree/master/kompute-shaders
kompute-shadershttps://github.com/albertjin/llama.cpp/tree/master/kompute-shaders
mediahttps://github.com/albertjin/llama.cpp/tree/master/media
mediahttps://github.com/albertjin/llama.cpp/tree/master/media
modelshttps://github.com/albertjin/llama.cpp/tree/master/models
modelshttps://github.com/albertjin/llama.cpp/tree/master/models
pocshttps://github.com/albertjin/llama.cpp/tree/master/pocs
pocshttps://github.com/albertjin/llama.cpp/tree/master/pocs
promptshttps://github.com/albertjin/llama.cpp/tree/master/prompts
promptshttps://github.com/albertjin/llama.cpp/tree/master/prompts
requirementshttps://github.com/albertjin/llama.cpp/tree/master/requirements
requirementshttps://github.com/albertjin/llama.cpp/tree/master/requirements
scriptshttps://github.com/albertjin/llama.cpp/tree/master/scripts
scriptshttps://github.com/albertjin/llama.cpp/tree/master/scripts
spm-headershttps://github.com/albertjin/llama.cpp/tree/master/spm-headers
spm-headershttps://github.com/albertjin/llama.cpp/tree/master/spm-headers
testshttps://github.com/albertjin/llama.cpp/tree/master/tests
testshttps://github.com/albertjin/llama.cpp/tree/master/tests
.clang-tidyhttps://github.com/albertjin/llama.cpp/blob/master/.clang-tidy
.clang-tidyhttps://github.com/albertjin/llama.cpp/blob/master/.clang-tidy
.dockerignorehttps://github.com/albertjin/llama.cpp/blob/master/.dockerignore
.dockerignorehttps://github.com/albertjin/llama.cpp/blob/master/.dockerignore
.ecrchttps://github.com/albertjin/llama.cpp/blob/master/.ecrc
.ecrchttps://github.com/albertjin/llama.cpp/blob/master/.ecrc
.editorconfighttps://github.com/albertjin/llama.cpp/blob/master/.editorconfig
.editorconfighttps://github.com/albertjin/llama.cpp/blob/master/.editorconfig
.flake8https://github.com/albertjin/llama.cpp/blob/master/.flake8
.flake8https://github.com/albertjin/llama.cpp/blob/master/.flake8
.gitignorehttps://github.com/albertjin/llama.cpp/blob/master/.gitignore
.gitignorehttps://github.com/albertjin/llama.cpp/blob/master/.gitignore
.gitmoduleshttps://github.com/albertjin/llama.cpp/blob/master/.gitmodules
.gitmoduleshttps://github.com/albertjin/llama.cpp/blob/master/.gitmodules
.pre-commit-config.yamlhttps://github.com/albertjin/llama.cpp/blob/master/.pre-commit-config.yaml
.pre-commit-config.yamlhttps://github.com/albertjin/llama.cpp/blob/master/.pre-commit-config.yaml
AUTHORShttps://github.com/albertjin/llama.cpp/blob/master/AUTHORS
AUTHORShttps://github.com/albertjin/llama.cpp/blob/master/AUTHORS
CMakeLists.txthttps://github.com/albertjin/llama.cpp/blob/master/CMakeLists.txt
CMakeLists.txthttps://github.com/albertjin/llama.cpp/blob/master/CMakeLists.txt
LICENSEhttps://github.com/albertjin/llama.cpp/blob/master/LICENSE
LICENSEhttps://github.com/albertjin/llama.cpp/blob/master/LICENSE
Makefilehttps://github.com/albertjin/llama.cpp/blob/master/Makefile
Makefilehttps://github.com/albertjin/llama.cpp/blob/master/Makefile
Package.swifthttps://github.com/albertjin/llama.cpp/blob/master/Package.swift
Package.swifthttps://github.com/albertjin/llama.cpp/blob/master/Package.swift
README-sycl.mdhttps://github.com/albertjin/llama.cpp/blob/master/README-sycl.md
README-sycl.mdhttps://github.com/albertjin/llama.cpp/blob/master/README-sycl.md
README.mdhttps://github.com/albertjin/llama.cpp/blob/master/README.md
README.mdhttps://github.com/albertjin/llama.cpp/blob/master/README.md
SECURITY.mdhttps://github.com/albertjin/llama.cpp/blob/master/SECURITY.md
SECURITY.mdhttps://github.com/albertjin/llama.cpp/blob/master/SECURITY.md
build.zighttps://github.com/albertjin/llama.cpp/blob/master/build.zig
build.zighttps://github.com/albertjin/llama.cpp/blob/master/build.zig
codecov.ymlhttps://github.com/albertjin/llama.cpp/blob/master/codecov.yml
codecov.ymlhttps://github.com/albertjin/llama.cpp/blob/master/codecov.yml
convert-hf-to-gguf-update.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-hf-to-gguf-update.py
convert-hf-to-gguf-update.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-hf-to-gguf-update.py
convert-hf-to-gguf.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-hf-to-gguf.py
convert-hf-to-gguf.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-hf-to-gguf.py
convert-llama-ggml-to-gguf.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-llama-ggml-to-gguf.py
convert-llama-ggml-to-gguf.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-llama-ggml-to-gguf.py
convert-lora-to-ggml.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-lora-to-ggml.py
convert-lora-to-ggml.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-lora-to-ggml.py
convert-persimmon-to-gguf.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-persimmon-to-gguf.py
convert-persimmon-to-gguf.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert-persimmon-to-gguf.py
convert.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert.py
convert.pyhttps://github.com/albertjin/llama.cpp/blob/master/convert.py
flake.lockhttps://github.com/albertjin/llama.cpp/blob/master/flake.lock
flake.lockhttps://github.com/albertjin/llama.cpp/blob/master/flake.lock
flake.nixhttps://github.com/albertjin/llama.cpp/blob/master/flake.nix
flake.nixhttps://github.com/albertjin/llama.cpp/blob/master/flake.nix
ggml-alloc.chttps://github.com/albertjin/llama.cpp/blob/master/ggml-alloc.c
ggml-alloc.chttps://github.com/albertjin/llama.cpp/blob/master/ggml-alloc.c
ggml-alloc.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-alloc.h
ggml-alloc.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-alloc.h
ggml-backend-impl.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-backend-impl.h
ggml-backend-impl.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-backend-impl.h
ggml-backend.chttps://github.com/albertjin/llama.cpp/blob/master/ggml-backend.c
ggml-backend.chttps://github.com/albertjin/llama.cpp/blob/master/ggml-backend.c
ggml-backend.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-backend.h
ggml-backend.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-backend.h
ggml-common.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-common.h
ggml-common.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-common.h
ggml-cuda.cuhttps://github.com/albertjin/llama.cpp/blob/master/ggml-cuda.cu
ggml-cuda.cuhttps://github.com/albertjin/llama.cpp/blob/master/ggml-cuda.cu
ggml-cuda.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-cuda.h
ggml-cuda.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-cuda.h
ggml-impl.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-impl.h
ggml-impl.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-impl.h
ggml-kompute.cpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-kompute.cpp
ggml-kompute.cpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-kompute.cpp
ggml-kompute.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-kompute.h
ggml-kompute.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-kompute.h
ggml-metal.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-metal.h
ggml-metal.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-metal.h
ggml-metal.mhttps://github.com/albertjin/llama.cpp/blob/master/ggml-metal.m
ggml-metal.mhttps://github.com/albertjin/llama.cpp/blob/master/ggml-metal.m
ggml-metal.metalhttps://github.com/albertjin/llama.cpp/blob/master/ggml-metal.metal
ggml-metal.metalhttps://github.com/albertjin/llama.cpp/blob/master/ggml-metal.metal
ggml-mpi.chttps://github.com/albertjin/llama.cpp/blob/master/ggml-mpi.c
ggml-mpi.chttps://github.com/albertjin/llama.cpp/blob/master/ggml-mpi.c
ggml-mpi.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-mpi.h
ggml-mpi.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-mpi.h
ggml-opencl.cpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-opencl.cpp
ggml-opencl.cpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-opencl.cpp
ggml-opencl.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-opencl.h
ggml-opencl.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-opencl.h
ggml-quants.chttps://github.com/albertjin/llama.cpp/blob/master/ggml-quants.c
ggml-quants.chttps://github.com/albertjin/llama.cpp/blob/master/ggml-quants.c
ggml-quants.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-quants.h
ggml-quants.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-quants.h
ggml-sycl.cpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-sycl.cpp
ggml-sycl.cpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-sycl.cpp
ggml-sycl.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-sycl.h
ggml-sycl.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-sycl.h
ggml-vulkan-shaders.hpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-vulkan-shaders.hpp
ggml-vulkan-shaders.hpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-vulkan-shaders.hpp
ggml-vulkan.cpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-vulkan.cpp
ggml-vulkan.cpphttps://github.com/albertjin/llama.cpp/blob/master/ggml-vulkan.cpp
ggml-vulkan.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-vulkan.h
ggml-vulkan.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml-vulkan.h
ggml.chttps://github.com/albertjin/llama.cpp/blob/master/ggml.c
ggml.chttps://github.com/albertjin/llama.cpp/blob/master/ggml.c
ggml.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml.h
ggml.hhttps://github.com/albertjin/llama.cpp/blob/master/ggml.h
ggml_vk_generate_shaders.pyhttps://github.com/albertjin/llama.cpp/blob/master/ggml_vk_generate_shaders.py
ggml_vk_generate_shaders.pyhttps://github.com/albertjin/llama.cpp/blob/master/ggml_vk_generate_shaders.py
llama.cpphttps://github.com/albertjin/llama.cpp/blob/master/llama.cpp
llama.cpphttps://github.com/albertjin/llama.cpp/blob/master/llama.cpp
llama.hhttps://github.com/albertjin/llama.cpp/blob/master/llama.h
llama.hhttps://github.com/albertjin/llama.cpp/blob/master/llama.h
mypy.inihttps://github.com/albertjin/llama.cpp/blob/master/mypy.ini
mypy.inihttps://github.com/albertjin/llama.cpp/blob/master/mypy.ini
requirements.txthttps://github.com/albertjin/llama.cpp/blob/master/requirements.txt
requirements.txthttps://github.com/albertjin/llama.cpp/blob/master/requirements.txt
sgemm.cpphttps://github.com/albertjin/llama.cpp/blob/master/sgemm.cpp
sgemm.cpphttps://github.com/albertjin/llama.cpp/blob/master/sgemm.cpp
sgemm.hhttps://github.com/albertjin/llama.cpp/blob/master/sgemm.h
sgemm.hhttps://github.com/albertjin/llama.cpp/blob/master/sgemm.h
unicode-data.cpphttps://github.com/albertjin/llama.cpp/blob/master/unicode-data.cpp
unicode-data.cpphttps://github.com/albertjin/llama.cpp/blob/master/unicode-data.cpp
unicode-data.hhttps://github.com/albertjin/llama.cpp/blob/master/unicode-data.h
unicode-data.hhttps://github.com/albertjin/llama.cpp/blob/master/unicode-data.h
unicode.cpphttps://github.com/albertjin/llama.cpp/blob/master/unicode.cpp
unicode.cpphttps://github.com/albertjin/llama.cpp/blob/master/unicode.cpp
unicode.hhttps://github.com/albertjin/llama.cpp/blob/master/unicode.h
unicode.hhttps://github.com/albertjin/llama.cpp/blob/master/unicode.h
READMEhttps://github.com/albertjin/llama.cpp
Licensehttps://github.com/albertjin/llama.cpp
Securityhttps://github.com/albertjin/llama.cpp
https://github.com/albertjin/llama.cpp#llamacpp
https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png
https://opensource.org/licenses/MIT
Roadmaphttps://github.com/users/ggerganov/projects/7
Project statushttps://github.com/ggerganov/llama.cpp/discussions/3471
Manifestohttps://github.com/ggerganov/llama.cpp/discussions/205
ggmlhttps://github.com/ggerganov/ggml
LLaMAhttps://arxiv.org/abs/2302.13971
https://github.com/albertjin/llama.cpp#recent-api-changes
ggml-org#6807https://github.com/ggml-org/llama.cpp/pull/6807
ggml-org#6341https://github.com/ggml-org/llama.cpp/pull/6341
ggml-org#6122https://github.com/ggml-org/llama.cpp/pull/6122
ggml-org#6017https://github.com/ggml-org/llama.cpp/pull/6017
ggml-org#5328https://github.com/ggml-org/llama.cpp/pull/5328
ggml-org#5796https://github.com/ggml-org/llama.cpp/pull/5796
ggml-org#5849https://github.com/ggml-org/llama.cpp/pull/5849
https://github.com/albertjin/llama.cpp#hot-topics
ggml-org#6920https://github.com/ggml-org/llama.cpp/pull/6920
ggml-org#6387https://github.com/ggml-org/llama.cpp/pull/6387
ggml-org#6404https://github.com/ggml-org/llama.cpp/discussions/6404
ggml-org#6225https://github.com/ggml-org/llama.cpp/pull/6225
ggml-org#6017https://github.com/ggml-org/llama.cpp/pull/6017
ggml-org#5981https://github.com/ggml-org/llama.cpp/issues/5981
ggml-org#5962https://github.com/ggml-org/llama.cpp/discussions/5962
ggml-org#5328https://github.com/ggml-org/llama.cpp/pull/5328
Descriptionhttps://github.com/albertjin/llama.cpp#description
Usagehttps://github.com/albertjin/llama.cpp#usage
Get the Codehttps://github.com/albertjin/llama.cpp#get-the-code
Buildhttps://github.com/albertjin/llama.cpp#build
BLAS Buildhttps://github.com/albertjin/llama.cpp#blas-build
Prepare and Quantizehttps://github.com/albertjin/llama.cpp#prepare-and-quantize
Run the quantized modelhttps://github.com/albertjin/llama.cpp#run-the-quantized-model
Memory/Disk Requirementshttps://github.com/albertjin/llama.cpp#memorydisk-requirements
Quantizationhttps://github.com/albertjin/llama.cpp#quantization
Interactive modehttps://github.com/albertjin/llama.cpp#interactive-mode
Constrained output with grammarshttps://github.com/albertjin/llama.cpp#constrained-output-with-grammars
Instruct modehttps://github.com/albertjin/llama.cpp#instruct-mode
Obtaining and using the Facebook LLaMA 2 modelhttps://github.com/albertjin/llama.cpp#obtaining-and-using-the-facebook-llama-2-model
Seminal papers and background on the modelshttps://github.com/albertjin/llama.cpp#seminal-papers-and-background-on-the-models
Perplexity (measuring model quality)https://github.com/albertjin/llama.cpp#perplexity-measuring-model-quality
Androidhttps://github.com/albertjin/llama.cpp#android
Dockerhttps://github.com/albertjin/llama.cpp#docker
Contributinghttps://github.com/albertjin/llama.cpp#contributing
Coding guidelineshttps://github.com/albertjin/llama.cpp#coding-guidelines
Docshttps://github.com/albertjin/llama.cpp#docs
https://github.com/albertjin/llama.cpp#description
inceptionhttps://github.com/ggerganov/llama.cpp/issues/33#issuecomment-1465108022
ggmlhttps://github.com/ggerganov/ggml
Mistral 7Bhttps://huggingface.co/mistralai/Mistral-7B-v0.1
Mixtral MoEhttps://huggingface.co/models?search=mistral-ai/Mixtral
DBRXhttps://huggingface.co/databricks/dbrx-instruct
Falconhttps://huggingface.co/models?search=tiiuae/falcon
Chinese LLaMA / Alpacahttps://github.com/ymcui/Chinese-LLaMA-Alpaca
Chinese LLaMA-2 / Alpaca-2https://github.com/ymcui/Chinese-LLaMA-Alpaca-2
Vigogne (French)https://github.com/bofenghuang/vigogne
Koalahttps://bair.berkeley.edu/blog/2023/04/03/koala/
Baichuan 1 & 2https://huggingface.co/models?search=baichuan-inc/Baichuan
derivationshttps://huggingface.co/hiyouga/baichuan-7b-sft
Aquila 1 & 2https://huggingface.co/models?search=BAAI/Aquila
Starcoder modelshttps://github.com/ggerganov/llama.cpp/pull/3187
Refacthttps://huggingface.co/smallcloudai/Refact-1_6B-fim
Persimmon 8Bhttps://github.com/ggerganov/llama.cpp/pull/3410
MPThttps://github.com/ggerganov/llama.cpp/pull/3417
Bloomhttps://github.com/ggerganov/llama.cpp/pull/3553
Yi modelshttps://huggingface.co/models?search=01-ai/Yi
StableLM modelshttps://huggingface.co/stabilityai
Deepseek modelshttps://huggingface.co/models?search=deepseek-ai/deepseek
Qwen modelshttps://huggingface.co/models?search=Qwen/Qwen
PLaMo-13Bhttps://github.com/ggerganov/llama.cpp/pull/3557
Phi modelshttps://huggingface.co/models?search=microsoft/phi
GPT-2https://huggingface.co/gpt2
Orion 14Bhttps://github.com/ggerganov/llama.cpp/pull/5118
InternLM2https://huggingface.co/models?search=internlm2
CodeShellhttps://github.com/WisdomShell/codeshell
Gemmahttps://ai.google.dev/gemma
Mambahttps://github.com/state-spaces/mamba
Grok-1https://huggingface.co/keyfan/grok-1-hf
Xversehttps://huggingface.co/models?search=xverse
Command-R modelshttps://huggingface.co/models?search=CohereForAI/c4ai-command-r
SEA-LIONhttps://huggingface.co/models?search=sea-lion
GritLM-7Bhttps://huggingface.co/GritLM/GritLM-7B
GritLM-8x7Bhttps://huggingface.co/GritLM/GritLM-8x7B
OLMohttps://allenai.org/olmo
HOWTO-add-model.mdhttps://github.com/albertjin/llama.cpp/blob/master/docs/HOWTO-add-model.md
LLaVA 1.5 modelshttps://huggingface.co/collections/liuhaotian/llava-15-653aac15d994e992e2677a7e
LLaVA 1.6 modelshttps://huggingface.co/collections/liuhaotian/llava-16-65b9e40155f60fd046a5ccf2
BakLLaVAhttps://huggingface.co/models?search=SkunkworksAI/Bakllava
Obsidianhttps://huggingface.co/NousResearch/Obsidian-3B-V0.5
ShareGPT4Vhttps://huggingface.co/models?search=Lin-Chen/ShareGPT4V
MobileVLM 1.7B/3B modelshttps://huggingface.co/models?search=mobileVLM
Yi-VLhttps://huggingface.co/models?search=Yi-VL
Mini CPMhttps://huggingface.co/models?search=MiniCPM
Moondreamhttps://huggingface.co/vikhyatk/moondream2
llama.cpp web serverhttps://github.com/albertjin/llama.cpp/blob/master/examples/server
OpenAI APIhttps://github.com/openai/openai-openapi
abetlen/llama-cpp-pythonhttps://github.com/abetlen/llama-cpp-python
go-skynet/go-llama.cpphttps://github.com/go-skynet/go-llama.cpp
withcatai/node-llama-cpphttps://github.com/withcatai/node-llama-cpp
lgrammel/modelfusionhttps://modelfusion.dev/integration/model-provider/llamacpp
tangledgroup/llama-cpp-wasmhttps://github.com/tangledgroup/llama-cpp-wasm
ngxson/wllamahttps://github.com/ngxson/wllama
yoshoku/llama_cpp.rbhttps://github.com/yoshoku/llama_cpp.rb
edgenai/llama_cpp-rshttps://github.com/edgenai/llama_cpp-rs
mdrokz/rust-llama.cpphttps://github.com/mdrokz/rust-llama.cpp
utilityai/llama-cpp-rshttps://github.com/utilityai/llama-cpp-rs
SciSharp/LLamaSharphttps://github.com/SciSharp/LLamaSharp
donderom/llm4shttps://github.com/donderom/llm4s
phronmophobic/llama.cljhttps://github.com/phronmophobic/llama.clj
mybigday/llama.rnhttps://github.com/mybigday/llama.rn
kherud/java-llama.cpphttps://github.com/kherud/java-llama.cpp
deins/llama.cpp.zighttps://github.com/Deins/llama.cpp.zig
netdur/llama_cpp_darthttps://github.com/netdur/llama_cpp_dart
distantmagic/resonancehttps://github.com/distantmagic/resonance
(more info)https://github.com/ggerganov/llama.cpp/pull/6326
iohub/collamahttps://github.com/iohub/coLLaMA
janhq/janhttps://github.com/janhq/jan
nat/openplaygroundhttps://github.com/nat/openplayground
Faradayhttps://faraday.dev/
LMStudiohttps://lmstudio.ai/
LocalAIhttps://github.com/mudler/LocalAI
LostRuins/koboldcpphttps://github.com/LostRuins/koboldcpp
Mozilla-Ocho/llamafilehttps://github.com/Mozilla-Ocho/llamafile
nomic-ai/gpt4allhttps://github.com/nomic-ai/gpt4all
ollama/ollamahttps://github.com/ollama/ollama
oobabooga/text-generation-webuihttps://github.com/oobabooga/text-generation-webui
psugihara/FreeChathttps://github.com/psugihara/FreeChat
cztomsik/avahttps://github.com/cztomsik/ava
ptsochantaris/emeltalhttps://github.com/ptsochantaris/emeltal
pythops/tenerehttps://github.com/pythops/tenere
RecurseChathttps://recurse.chat/
semperai/amicahttps://github.com/semperai/amica
withcatai/cataihttps://github.com/withcatai/catai
Mobile-Artificial-Intelligence/maidhttps://github.com/Mobile-Artificial-Intelligence/maid
Mstyhttps://msty.app
LLMFarmhttps://github.com/guinmoon/LLMFarm?tab=readme-ov-file
KanTVhttps://github.com/zhouwg/kantv?tab=readme-ov-file
Dothttps://github.com/alexpinel/Dot
MindMachttps://mindmac.app
KodiBothttps://github.com/firatkiral/kodibot
evahttps://github.com/ylsdamxssjxxdd/eva
AI Sublime Text pluginhttps://github.com/yaroslavyaroslav/OpenAI-sublime-text
whisper.cpphttps://github.com/ggerganov/whisper.cpp
https://github.com/albertjin/llama.cpp#usage
https://github.com/albertjin/llama.cpp#get-the-code
https://github.com/albertjin/llama.cpp#build
w64devkithttps://github.com/skeeto/w64devkit/releases
DRM in FreeBSDhttps://wiki.freebsd.org/Graphics
https://github.com/albertjin/llama.cpp#metal-build
https://github.com/albertjin/llama.cpp#mpi-build
MPICHhttps://www.mpich.org
OpenMPIhttps://www.open-mpi.org
https://github.com/albertjin/llama.cpp#blas-build
https://github.com/albertjin/llama.cpp#accelerate-framework
https://github.com/albertjin/llama.cpp#openblas
w64devkithttps://github.com/skeeto/w64devkit/releases
OpenBLAS for Windowshttps://github.com/xianyi/OpenBLAS/releases
https://github.com/albertjin/llama.cpp#blis
BLIS.mdhttps://github.com/albertjin/llama.cpp/blob/master/docs/BLIS.md
https://github.com/albertjin/llama.cpp#sycl
llama.cpp for SYCLhttps://github.com/albertjin/llama.cpp/blob/master/README-sycl.md
https://github.com/albertjin/llama.cpp#intel-onemkl
llama.cpp for SYCLhttps://github.com/albertjin/llama.cpp/blob/master/README-sycl.md
oneAPI-basekithttps://hub.docker.com/r/intel/oneapi-basekit
Optimizing and Running LLaMA2 on Intel® CPUhttps://www.intel.com/content/www/us/en/content-details/791610/optimizing-and-running-llama2-on-intel-cpu.html
https://github.com/albertjin/llama.cpp#cuda
CUDA Toolkithttps://developer.nvidia.com/cuda-downloads
Offical Supporthttps://www.jetson-ai-lab.com/tutorial_text-generation.html
CUDA_VISIBLE_DEVICEShttps://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars
https://github.com/albertjin/llama.cpp#hipblas
ROCm Quick Start (Linux)https://rocm.docs.amd.com/projects/install-on-linux/en/latest/tutorial/quick-start.html#rocm-install-quick
herehttps://llvm.org/docs/AMDGPUUsage.html#processors
HIP_VISIBLE_DEVICEShttps://rocm.docs.amd.com/en/latest/understand/gpu_isolation.html#hip-visible-devices
https://github.com/albertjin/llama.cpp#clblast
CLBlasthttps://github.com/CNugteren/CLBlast
OpenCL SDKhttps://github.com/KhronosGroup/OpenCL-SDK
OpenCL Releaseshttps://github.com/KhronosGroup/OpenCL-SDK/releases
https://github.com/albertjin/llama.cpp#installing-clblast
CLBlast Releaseshttps://github.com/CNugteren/CLBlast/releases
https://github.com/albertjin/llama.cpp#building-llama-with-clblast
https://github.com/albertjin/llama.cpp#running-llama-with-clblast
https://github.com/albertjin/llama.cpp#vulkan
Vulkan SDKhttps://vulkan.lunarg.com/doc/view/latest/linux/getting_started_ubuntu.html
https://github.com/albertjin/llama.cpp#prepare-and-quantize
Obtaining and using the Facebook LLaMA 2 modelhttps://github.com/albertjin/llama.cpp#obtaining-and-using-the-facebook-llama-2-model
https://github.com/albertjin/llama.cpp#run-the-quantized-model
https://github.com/albertjin/llama.cpp#running-on-windows-with-prebuilt-binaries
https://github.com/albertjin/llama.cpp#memorydisk-requirements
https://github.com/albertjin/llama.cpp#quantization
k-quantshttps://github.com/ggerganov/llama.cpp/pull/1684
#2707https://github.com/ggerganov/llama.cpp/pull/2707
#2807https://github.com/ggerganov/llama.cpp/pull/2807
#4773 - 2-bit i-quants (inference)https://github.com/ggerganov/llama.cpp/pull/4773
#4856 - 2-bit i-quants (inference)https://github.com/ggerganov/llama.cpp/pull/4856
#4861 - importance matrixhttps://github.com/ggerganov/llama.cpp/pull/4861
#4872 - MoE modelshttps://github.com/ggerganov/llama.cpp/pull/4872
#4897 - 2-bit quantizationhttps://github.com/ggerganov/llama.cpp/pull/4897
#4930 - imatrix for all k-quantshttps://github.com/ggerganov/llama.cpp/pull/4930
#4951 - imatrix on the GPUhttps://github.com/ggerganov/llama.cpp/pull/4957
#4969 - imatrix for legacy quantshttps://github.com/ggerganov/llama.cpp/pull/4969
#4996 - k-qunats tuninghttps://github.com/ggerganov/llama.cpp/pull/4996
#5060 - Q3_K_XShttps://github.com/ggerganov/llama.cpp/pull/5060
#5196 - 3-bit i-quantshttps://github.com/ggerganov/llama.cpp/pull/5196
quantization tuninghttps://github.com/ggerganov/llama.cpp/pull/5320
another onehttps://github.com/ggerganov/llama.cpp/pull/5334
another onehttps://github.com/ggerganov/llama.cpp/pull/5361
https://github.com/albertjin/llama.cpp#perplexity-measuring-model-quality
https://huggingface.co/docs/transformers/perplexityhttps://huggingface.co/docs/transformers/perplexity
https://paperswithcode.com/dataset/wikitext-2https://paperswithcode.com/dataset/wikitext-2
https://github.com/albertjin/llama.cpp#how-to-run
https://huggingface.co/datasets/ggml-org/ci/resolve/main/wikitext-2-raw-v1.ziphttps://huggingface.co/datasets/ggml-org/ci/resolve/main/wikitext-2-raw-v1.zip
https://github.com/albertjin/llama.cpp#interactive-mode
READMEhttps://github.com/albertjin/llama.cpp/blob/master/examples/main/README.md
https://user-images.githubusercontent.com/1991296/224575029-2af3c7dc-5a65-4f64-a6bb-517a532aea38.png
https://github.com/albertjin/llama.cpp#persistent-interaction
https://github.com/albertjin/llama.cpp#constrained-output-with-grammars
GBNF Guidehttps://github.com/albertjin/llama.cpp/blob/master/grammars/README.md
https://grammar.intrinsiclabs.ai/https://grammar.intrinsiclabs.ai/
its repohttp://github.com/intrinsiclabsai/gbnfgen
https://github.com/albertjin/llama.cpp#instruct-mode
https://github.com/albertjin/llama.cpp#obtaining-and-using-the-facebook-llama-2-model
Facebook's LLaMA download pagehttps://ai.meta.com/resources/models-and-libraries/llama-downloads/
TheBlokehttps://huggingface.co/TheBloke
LLaMA 2 7B basehttps://huggingface.co/TheBloke/Llama-2-7B-GGUF
LLaMA 2 13B basehttps://huggingface.co/TheBloke/Llama-2-13B-GGUF
LLaMA 2 70B basehttps://huggingface.co/TheBloke/Llama-2-70B-GGUF
LLaMA 2 7B chathttps://huggingface.co/TheBloke/Llama-2-7B-chat-GGUF
LLaMA 2 13B chathttps://huggingface.co/TheBloke/Llama-2-13B-chat-GGUF
LLaMA 2 70B chathttps://huggingface.co/TheBloke/Llama-2-70B-chat-GGUF
https://github.com/albertjin/llama.cpp#seminal-papers-and-background-on-the-models
Introducing LLaMA: A foundational, 65-billion-parameter large language modelhttps://ai.facebook.com/blog/large-language-model-llama-meta-ai/
LLaMA: Open and Efficient Foundation Language Modelshttps://arxiv.org/abs/2302.13971
Language Models are Few-Shot Learnershttps://arxiv.org/abs/2005.14165
Aligning language models to follow instructionshttps://openai.com/research/instruction-following
Training language models to follow instructions with human feedbackhttps://arxiv.org/abs/2203.02155
https://github.com/albertjin/llama.cpp#android
https://github.com/albertjin/llama.cpp#building-the-project-using-android-ndk
termuxhttps://termux.dev/
Android NDKhttps://developer.android.com/ndk
termuxhttps://termux.dev/
llama-2-7b-chat.Q4_K_M.ggufhttps://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_M.gguf
https://github.com/albertjin/llama.cpp#build-on-android-using-termux
Termuxhttps://github.com/termux/termux-app#installation
Follow the Linux build instructionshttps://github.com/ggerganov/llama.cpp#build
https://github.com/albertjin/llama.cpp#docker
https://github.com/albertjin/llama.cpp#prerequisites
https://github.com/albertjin/llama.cpp#images
.devops/https://github.com/albertjin/llama.cpp/blob/master/.devops
.github/workflows/docker.ymlhttps://github.com/albertjin/llama.cpp/blob/master/.github/workflows/docker.yml
https://github.com/albertjin/llama.cpp#usage-1
https://github.com/albertjin/llama.cpp#docker-with-cuda
nvidia-container-toolkithttps://github.com/NVIDIA/nvidia-container-toolkit
https://github.com/albertjin/llama.cpp#building-locally
https://github.com/albertjin/llama.cpp#usage-2
https://github.com/albertjin/llama.cpp#contributing
Inference at the edgehttps://github.com/ggerganov/llama.cpp/discussions/205
Changelog podcasthttps://changelog.com/podcast/532
https://github.com/albertjin/llama.cpp#coding-guidelines
good first issueshttps://github.com/ggerganov/llama.cpp/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22
C = ggml_mul_mat(ctx, A, B)https://github.com/ggerganov/llama.cpp/blob/880e352277fc017df4d5794f0c21c44e1eae2b84/ggml.h#L1058-L1064
https://github.com/albertjin/llama.cpp/blob/master/media/matmul.png
https://github.com/albertjin/llama.cpp#docs
mainhttps://github.com/albertjin/llama.cpp/blob/master/examples/main/README.md
serverhttps://github.com/albertjin/llama.cpp/blob/master/examples/server/README.md
jeopardyhttps://github.com/albertjin/llama.cpp/blob/master/examples/jeopardy/README.md
BLIShttps://github.com/albertjin/llama.cpp/blob/master/docs/BLIS.md
Performance troubleshootinghttps://github.com/albertjin/llama.cpp/blob/master/docs/token_generation_performance_tips.md
GGML tips & trickshttps://github.com/ggerganov/llama.cpp/wiki/GGML-Tips-&-Tricks
GBNF grammarshttps://github.com/albertjin/llama.cpp/blob/master/grammars/README.md
Readme https://github.com/albertjin/llama.cpp#readme-ov-file
MIT license https://github.com/albertjin/llama.cpp#MIT-1-ov-file
Security policy https://github.com/albertjin/llama.cpp#security-ov-file
Please reload this pagehttps://github.com/albertjin/llama.cpp
Activityhttps://github.com/albertjin/llama.cpp/activity
0 forkshttps://github.com/albertjin/llama.cpp/forks
Report repository https://github.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2Falbertjin%2Fllama.cpp&report=albertjin+%28user%29
Releaseshttps://github.com/albertjin/llama.cpp/releases
Packages 0https://github.com/users/albertjin/packages?repo_name=llama.cpp
Please reload this pagehttps://github.com/albertjin/llama.cpp
Contributorshttps://github.com/albertjin/llama.cpp/graphs/contributors
Please reload this pagehttps://github.com/albertjin/llama.cpp
https://github.com
Termshttps://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacyhttps://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Securityhttps://github.com/security
Statushttps://www.githubstatus.com/
Communityhttps://github.community/
Docshttps://docs.github.com/
Contacthttps://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.