René's URL Explorer Experiment


Title: GitHub - lsxxh/llama-cpp-python: Efficient Python bindings for the llama.cpp library · GitHub

Open Graph Title: GitHub - lsxxh/llama-cpp-python: Efficient Python bindings for the llama.cpp library

X Title: GitHub - lsxxh/llama-cpp-python: Efficient Python bindings for the llama.cpp library

Description: Efficient Python bindings for the llama.cpp library - lsxxh/llama-cpp-python

Open Graph Description: Efficient Python bindings for the llama.cpp library - lsxxh/llama-cpp-python

X Description: Efficient Python bindings for the llama.cpp library - lsxxh/llama-cpp-python

Opengraph URL: https://github.com/lsxxh/llama-cpp-python

X: @github

direct link

Domain: github.com

react-profiling0
react-import-mapreact,react-dom,react-dom/client,react-dom/profiling,react-is,react/compiler-runtime,react/jsx-dev-runtime,react/jsx-runtime,scheduler@b8488ee2c322
route-pattern/:user_id/:repository
route-controllerfiles
route-actiondisambiguate
fetch-noncev2:ac7a3b86-fe6c-a442-2463-d2dd2f05656b
current-catalog-service-hashf3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-idCBDE:5314B:FF8F79:140867B:6AFF89D4
html-safe-nonce78e9867b801e0febcfc7592d1ac7d4b447f3c95bec8d04a1fa9c34bca6cdd963
visitor-payloadeyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJDQkRFOjUzMTRCOkZGOEY3OToxNDA4NjdCOjZBRkY4OUQ0IiwidmlzaXRvcl9pZCI6IjU4NTIzODczMjMzOTU2NzI1MzIiLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmac89d56e5cbf8b560276648ce2d7721d16356d333786652abf26b4ad3127c53da3
hovercard-subject-tagrepository:1344400880
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/lsxxh/llama-cpp-python
twitter:imagehttps://opengraph.githubassets.com/8038a495e1672ec7b22432dc2191155c2b45ef6a015b08cf0e3e6f83cf05a608/lsxxh/llama-cpp-python
twitter:cardsummary_large_image
og:imagehttps://opengraph.githubassets.com/8038a495e1672ec7b22432dc2191155c2b45ef6a015b08cf0e3e6f83cf05a608/lsxxh/llama-cpp-python
og:image:altEfficient Python bindings for the llama.cpp library - lsxxh/llama-cpp-python
og:image:width1200
og:image:height600
og:site_nameGitHub
og:typeobject
hostnamegithub.com
expected-hostnamegithub.com
None587ad99a3e443b2e1cb0d3df059ec49ab54389861f13310766dfdeb615fed90d
turbo-cache-controlno-cache
go-importgithub.com/lsxxh/llama-cpp-python git https://github.com/lsxxh/llama-cpp-python.git
octolytics-dimension-user_id42707880
octolytics-dimension-user_loginlsxxh
octolytics-dimension-repository_id1344400880
octolytics-dimension-repository_nwolsxxh/llama-cpp-python
octolytics-dimension-repository_publictrue
octolytics-dimension-repository_is_forktrue
octolytics-dimension-repository_parent_id920296412
octolytics-dimension-repository_parent_nwoJamePeng/llama-cpp-python
octolytics-dimension-repository_network_root_id617868717
octolytics-dimension-repository_network_root_nwoabetlen/llama-cpp-python
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
release5bb0fb68d64881d1344f5863d809515d496801e5
ui-targetfull
theme-color#1e2327
color-schemelight dark

Links:

Skip to contenthttps://github.com/lsxxh/llama-cpp-python#start-of-content
https://github.com/
Sign inhttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Flsxxh%2Fllama-cpp-python
GitHubRepository hosting, code review, and collaborationhttps://github.com/platform
CopilotAI coding agent for tasks, projects, and automated workhttps://github.com/features/copilot
ActionsCI/CD and automationhttps://github.com/features/actions
Code QualityQuality analysis, fixes, and enforcementhttps://github.com/features/code-quality
CodespacesCloud development environmentshttps://github.com/features/codespaces
Code SecurityVulnerability detection and remediationhttps://github.com/security/advanced-security/code-security
Secret ProtectionSecret scanning and leak preventionhttps://github.com/security/advanced-security/secret-protection
All Featureshttps://github.com/features
Documentationhttps://docs.github.com/en
Traininghttps://learn.github.com/skills
Certificationshttps://learn.github.com/credentials
Build with Copilothttps://github.com/features/ai
Customize Copilothttps://docs.github.com/en/copilot/how-tos/copilot-on-github/customize-copilot/customize-copilot-overview
Integrationshttps://github.com/marketplace
Trending reposhttps://github.com/trending
GitHub Sponsorshttps://github.com/open-source/sponsors
Developer articleshttps://github.com/resources/articles
ChangelogYour source for the latest features, improvements, and fixes across GitHub products, all in one place.https://github.blog/changelog/
Enterpriseshttps://github.com/enterprise
Teamhttps://github.com/team
Startupshttps://github.com/enterprise/startups
Nonprofitshttps://github.com/solutions/industry/nonprofits
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
See all industrieshttps://github.com/solutions/industry
Why GitHubhttps://github.com/why-github
Customer Storieshttps://github.com/customer-stories
Business insightshttps://github.com/solutions/executive-insights
Trust Centerhttps://github.com/trust-center
GitHub Advanced SecurityEnterprise-grade code securityhttps://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
Documentationhttps://docs.github.com/en
Resource centerhttps://github.com/resources
Bloghttps://github.blog/
Events & webinarshttps://github.com/resources/events
Community Forumhttps://github.com/orgs/community/discussions
Customer Storieshttps://github.com/customer-stories
Integrationshttps://github.com/marketplace
Customer supporthttps://help.github.com/
Traininghttps://learn.github.com/skills
GitHub Statushttps://www.githubstatus.com/
Abouthttps://github.com/about
Partnershttps://github.com/partners
Changeloghttps://github.blog/changelog/
GitHub UniverseThe event for developers, by developers — talks, workshops, and what’s next for GitHub.https://githubuniverse.com/
Pricinghttps://github.com/pricing
Sign inhttps://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Flsxxh%2Fllama-cpp-python
Sign uphttps://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=lsxxh%2Fllama-cpp-python
Reloadhttps://github.com/lsxxh/llama-cpp-python
Reloadhttps://github.com/lsxxh/llama-cpp-python
Reloadhttps://github.com/lsxxh/llama-cpp-python
lsxxhhttps://github.com/lsxxh
llama-cpp-pythonhttps://github.com/lsxxh/llama-cpp-python
Codehttps://github.com/lsxxh/llama-cpp-python
Pull requestshttps://github.com/lsxxh/llama-cpp-python/pulls
Actionshttps://github.com/lsxxh/llama-cpp-python/actions
Projectshttps://github.com/lsxxh/llama-cpp-python/projects
Security and qualityhttps://github.com/lsxxh/llama-cpp-python/security
Insightshttps://github.com/lsxxh/llama-cpp-python/pulse
https://github.com/lsxxh/llama-cpp-python
llama-cpp-pythonhttps://github.com/lsxxh/llama-cpp-python
JamePeng/llama-cpp-pythonhttps://github.com/JamePeng/llama-cpp-python
Notificationshttps://github.com/login?return_to=%2Flsxxh%2Fllama-cpp-python
Fork0 (0)https://github.com/login?return_to=%2Flsxxh%2Fllama-cpp-python
Star0 (0)https://github.com/login?return_to=%2Flsxxh%2Fllama-cpp-python
github.com/JamePeng/llama-cpp-python/wikihttps://github.com/JamePeng/llama-cpp-python/wiki
Readmehttps://github.com/lsxxh/llama-cpp-python#readme-ov-file
Licensehttps://github.com/lsxxh/llama-cpp-python#License-1-ov-file
Activityhttps://github.com/lsxxh/llama-cpp-python/activity
0 forkshttps://github.com/lsxxh/llama-cpp-python/forks
Report repositoryhttps://github.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2Flsxxh%2Fllama-cpp-python&report=lsxxh+%28user%29
Brancheshttps://github.com/lsxxh/llama-cpp-python/branches
Tagshttps://github.com/lsxxh/llama-cpp-python/tags
https://github.com/lsxxh/llama-cpp-python/branches
https://github.com/lsxxh/llama-cpp-python/tags
2,862 Commitshttps://github.com/lsxxh/llama-cpp-python/commits/main/
https://github.com/lsxxh/llama-cpp-python/commits/main/
.githubhttps://github.com/lsxxh/llama-cpp-python/tree/main/.github
.githubhttps://github.com/lsxxh/llama-cpp-python/tree/main/.github
dockerhttps://github.com/lsxxh/llama-cpp-python/tree/main/docker
dockerhttps://github.com/lsxxh/llama-cpp-python/tree/main/docker
docshttps://github.com/lsxxh/llama-cpp-python/tree/main/docs
docshttps://github.com/lsxxh/llama-cpp-python/tree/main/docs
exampleshttps://github.com/lsxxh/llama-cpp-python/tree/main/examples
exampleshttps://github.com/lsxxh/llama-cpp-python/tree/main/examples
llama_cpphttps://github.com/lsxxh/llama-cpp-python/tree/main/llama_cpp
llama_cpphttps://github.com/lsxxh/llama-cpp-python/tree/main/llama_cpp
scriptshttps://github.com/lsxxh/llama-cpp-python/tree/main/scripts
scriptshttps://github.com/lsxxh/llama-cpp-python/tree/main/scripts
testshttps://github.com/lsxxh/llama-cpp-python/tree/main/tests
testshttps://github.com/lsxxh/llama-cpp-python/tree/main/tests
tools/abihttps://github.com/lsxxh/llama-cpp-python/tree/main/tools/abi
tools/abihttps://github.com/lsxxh/llama-cpp-python/tree/main/tools/abi
vendorhttps://github.com/lsxxh/llama-cpp-python/tree/main/vendor
vendorhttps://github.com/lsxxh/llama-cpp-python/tree/main/vendor
.dockerignorehttps://github.com/lsxxh/llama-cpp-python/blob/main/.dockerignore
.dockerignorehttps://github.com/lsxxh/llama-cpp-python/blob/main/.dockerignore
.gitignorehttps://github.com/lsxxh/llama-cpp-python/blob/main/.gitignore
.gitignorehttps://github.com/lsxxh/llama-cpp-python/blob/main/.gitignore
.gitmoduleshttps://github.com/lsxxh/llama-cpp-python/blob/main/.gitmodules
.gitmoduleshttps://github.com/lsxxh/llama-cpp-python/blob/main/.gitmodules
CHANGELOG.mdhttps://github.com/lsxxh/llama-cpp-python/blob/main/CHANGELOG.md
CHANGELOG.mdhttps://github.com/lsxxh/llama-cpp-python/blob/main/CHANGELOG.md
CMakeLists.txthttps://github.com/lsxxh/llama-cpp-python/blob/main/CMakeLists.txt
CMakeLists.txthttps://github.com/lsxxh/llama-cpp-python/blob/main/CMakeLists.txt
LICENSE.mdhttps://github.com/lsxxh/llama-cpp-python/blob/main/LICENSE.md
LICENSE.mdhttps://github.com/lsxxh/llama-cpp-python/blob/main/LICENSE.md
Makefilehttps://github.com/lsxxh/llama-cpp-python/blob/main/Makefile
Makefilehttps://github.com/lsxxh/llama-cpp-python/blob/main/Makefile
README.mdhttps://github.com/lsxxh/llama-cpp-python/blob/main/README.md
README.mdhttps://github.com/lsxxh/llama-cpp-python/blob/main/README.md
pyproject.tomlhttps://github.com/lsxxh/llama-cpp-python/blob/main/pyproject.toml
pyproject.tomlhttps://github.com/lsxxh/llama-cpp-python/blob/main/pyproject.toml
READMEhttps://github.com/lsxxh/llama-cpp-python
Licensehttps://github.com/lsxxh/llama-cpp-python
https://github.com/lsxxh/llama-cpp-python/blob/main/docs/icon.png
llama.cpphttps://github.com/ggml-org/llama.cpp
https://github.com/lsxxh/llama-cpp-python#efficient-python-bindings-for-llamacpp-library
https://github.com/JamePeng/llama-cpp-python/actions/workflows/test.yaml
https://camo.githubusercontent.com/0026f4c164c97907dccf892a7d855514d9d14a6b559f659a1592113081ff192c/68747470733a2f2f696d672e736869656c64732e696f2f6769746875622f762f7461672f4a616d6550656e672f6c6c616d612d6370702d707974686f6e
https://pypi.org/project/llama-cpp-python/
https://pepy.tech/projects/llama-cpp-python
https://github.com/lsxxh/llama-cpp-python/blob/main
llama.cpphttps://github.com/ggml-org/llama.cpp
llama_cpp_libhttps://github.com/JamePeng/llama-cpp-python/blob/main/llama_cpp/llama_cpp.py
mtmd_cpp_libhttps://github.com/JamePeng/llama-cpp-python/blob/main/llama_cpp/mtmd_cpp.py
ggml_cpp_libhttps://github.com/JamePeng/llama-cpp-python/blob/main/llama_cpp/_ggml.py
llama_types.pyhttps://github.com/JamePeng/llama-cpp-python/blob/main/llama_cpp/llama_types.py
High-level APIhttps://github.com/JamePeng/llama-cpp-python#high-level-api
Continuing Assistant Responses (Prefill)https://github.com/JamePeng/llama-cpp-python#continuing-assistant-responses-prefill
Dynamic LoRA Routing & Control Vectors (Multi-Tenant Serving)https://github.com/JamePeng/llama-cpp-python#dynamic-lora-routing--control-vectors-multi-tenant-serving
Dynamic LoRA Examplehttps://github.com/JamePeng/llama-cpp-python#dynamic-lora-example
Control Vector Injection (Representation Engineering)https://github.com/JamePeng/llama-cpp-python#control-vector-injection-representation-engineering
Sampling Configuration & Usage (LlamaSamplingParams)https://github.com/JamePeng/llama-cpp-python#sampling-configuration--usage-llamasamplingparams
How to use the ReasoningBudgetSamplerhttps://github.com/JamePeng/llama-cpp-python#reasoning-budget-first-reasoning-block
Speculative Decodinghttps://github.com/JamePeng/llama-cpp-python#speculative-decoding
MTP speculative decodinghttps://github.com/JamePeng/llama-cpp-python#mtp-speculative-decoding
DFlash and DSpark speculative decodinghttps://github.com/JamePeng/llama-cpp-python#dflash-and-dspark-speculative-decoding
N-gram speculative decodinghttps://github.com/JamePeng/llama-cpp-python#n-gram-speculative-decoding
Multi-modal Models Supporthttps://github.com/JamePeng/llama-cpp-python#multi-modal-models
Introducing Generic MTMD Chat Handlerhttps://github.com/JamePeng/llama-cpp-python#generic-mtmd-chat-handler
Loading a Local Image With Qwen3VL(Thinking/Instruct)https://github.com/JamePeng/llama-cpp-python#loading-a-local-image-with-qwen3vlthinkinginstruct
Speech Recognition With Qwen3-ASR (Speech-to-Text)https://github.com/JamePeng/llama-cpp-python#speech-recognition-with-qwen3-asr-speech-to-text
Comprehensive Omni MultiModal Example: Gemma-4 (Vision + Audio + Text)https://github.com/JamePeng/llama-cpp-python#comprehensive-omni-multimodal-example-gemma-4-vision--audio--text
Embeddings & Reranking (GGUF)https://github.com/JamePeng/llama-cpp-python#embeddings--reranking-gguf
1. Text Embeddings (Vector Search)https://github.com/JamePeng/llama-cpp-python#1-text-embeddings-vector-search
2. Reranking (Cross-Encoder Scoring)https://github.com/JamePeng/llama-cpp-python#2-reranking-cross-encoder-scoring
3. Normalizationhttps://github.com/JamePeng/llama-cpp-python#3-normalization
FAQhttps://github.com/JamePeng/llama-cpp-python#faq
docs/wikihttps://github.com/JamePeng/llama-cpp-python/tree/main/docs/wiki
https://github.com/lsxxh/llama-cpp-python#discussions
GitHub Discussionshttps://github.com/JamePeng/llama-cpp-python/discussions
https://github.com/lsxxh/llama-cpp-python#installation
docs/wiki/install.mdhttps://github.com/JamePeng/llama-cpp-python/blob/main/docs/wiki/install.md
Visual Studio 2022 Build Toolshttps://download.visualstudio.microsoft.com/download/pr/6efb3484-905b-485c-8b5f-9d3a5f39e731/07908cd6d91e75b8ea4339d8f2cfa6e8d8bb4fd706af7b918ae391cd6fc2a066/vs_BuildTools.exe
https://github.com/lsxxh/llama-cpp-python#installation-configuration
llama.cpp build docshttps://github.com/ggml-org/llama.cpp/blob/master/docs/build.md
https://github.com/lsxxh/llama-cpp-python#supported-backends
https://developer.nvidia.com/cuda-toolkit-archivehttps://developer.nvidia.com/cuda-toolkit-archive
https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#cudahttps://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#cuda
https://github.com/JamePeng/llama-cpp-python/releaseshttps://github.com/JamePeng/llama-cpp-python/releases
https://github.com/lsxxh/llama-cpp-python#install-openvino-runtime
Linuxhttps://docs.openvino.ai/2026/get-started/install-openvino/install-openvino-archive-linux.html
Windowshttps://docs.openvino.ai/2026/get-started/install-openvino/install-openvino-archive-windows.html
https://github.com/lsxxh/llama-cpp-python#supported-devices
Intel hardwarehttps://docs.openvino.ai/2026/about-openvino/release-notes-openvino/system-requirements.html
https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/OPENVINO.mdhttps://github.com/ggml-org/llama.cpp/blob/master/docs/backend/OPENVINO.md
https://github.com/JamePeng/llama-cpp-python/releaseshttps://github.com/JamePeng/llama-cpp-python/releases
ROCm Quick Start (Linux)https://rocm.docs.amd.com/projects/install-on-linux/en/latest/tutorial/quick-start.html#rocm-install-quick
https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#hiphttps://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#hip
Vulkan SDKhttps://vulkan.lunarg.com/sdk/home#windows
Getting Started with the Linux Tarball Vulkan SDKhttps://vulkan.lunarg.com/doc/sdk/latest/linux/getting_started.html
Getting Started with the MacOS Vulkan SDKhttps://vulkan.lunarg.com/doc/sdk/latest/mac/getting_started.html
https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#vulkanhttps://github.com/ggml-org/llama.cpp/blob/master/docs/build.md#vulkan
https://github.com/lsxxh/llama-cpp-python#supported-os
https://github.com/lsxxh/llama-cpp-python#intel-gpu
oneAPI supported GPUhttps://www.intel.com/content/www/us/en/developer/articles/system-requirements/intel-oneapi-base-toolkit-system-requirements.html#inpage-nav-1-1
OpenCLhttps://github.com/lsxxh/llama-cpp-python/blob/main/docs/backend/OPENCL.md
https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/SYCL.mdhttps://github.com/ggml-org/llama.cpp/blob/master/docs/backend/SYCL.md
https://github.com/lsxxh/llama-cpp-python#install-notes
https://github.com/lsxxh/llama-cpp-python#windows-notes
https://github.com/lsxxh/llama-cpp-python#wheel-packaging-checklist
https://github.com/lsxxh/llama-cpp-python#upgrading-and-reinstalling
https://github.com/lsxxh/llama-cpp-python#high-level-api
API Referencehttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#high-level-api
Llamahttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama
__call__https://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama.__call__
create_completionhttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama.create_completion
Llamahttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama
Hugging Face Hubhttps://huggingface.co/models
https://github.com/lsxxh/llama-cpp-python#pulling-models-from-hugging-face-hub
from_pretrainedhttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama.from_pretrained
from_pretrainedhttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama.from_pretrained
hfhttps://huggingface.co/docs/huggingface_hub/en/guides/cli
https://github.com/lsxxh/llama-cpp-python#chat-completion
create_chat_completionhttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama.create_chat_completion
Llamahttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama
create_chat_completion_openai_v1https://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama.create_chat_completion_openai_v1
https://github.com/lsxxh/llama-cpp-python#json-and-json-schema-mode
create_chat_completionhttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#llama_cpp.Llama.create_chat_completion
https://github.com/lsxxh/llama-cpp-python#json-mode
https://github.com/lsxxh/llama-cpp-python#json-schema-mode
https://github.com/lsxxh/llama-cpp-python#function-calling
herehttps://huggingface.co/meetkai
https://github.com/lsxxh/llama-cpp-python#continuing-assistant-responses-prefill
https://github.com/lsxxh/llama-cpp-python#dynamic-lora-routing--control-vectors-multi-tenant-serving
https://github.com/lsxxh/llama-cpp-python#dynamic-lora-example
https://github.com/lsxxh/llama-cpp-python#control-vector-injection-representation-engineering
https://github.com/lsxxh/llama-cpp-python#sampling-configuration--usage-llamasamplingparams
https://github.com/lsxxh/llama-cpp-python#core-sampling-parameters
https://github.com/lsxxh/llama-cpp-python#advanced--experimental-samplers
https://github.com/lsxxh/llama-cpp-python#target-entropy-mirostat
https://github.com/lsxxh/llama-cpp-python#repetition-penalties
https://github.com/lsxxh/llama-cpp-python#constraints--callbacks
https://github.com/lsxxh/llama-cpp-python#reasoning-budget-first-reasoning-block
https://github.com/lsxxh/llama-cpp-python#️-usage-example
https://github.com/lsxxh/llama-cpp-python#speculative-decoding
llama-cpp-pythonhttps://github.com/JamePeng/llama-cpp-python
Llama Speculative Decodinghttps://github.com/JamePeng/llama-cpp-python/blob/main/docs/wiki/modules/LlamaSpeculative.md
https://github.com/lsxxh/llama-cpp-python#mtp-speculative-decoding
https://github.com/lsxxh/llama-cpp-python#built-in-mtp
https://github.com/lsxxh/llama-cpp-python#external-mtp-model
https://github.com/lsxxh/llama-cpp-python#dflash-and-dspark-speculative-decoding
https://github.com/lsxxh/llama-cpp-python#n-gram-speculative-decoding
https://github.com/lsxxh/llama-cpp-python#runtime-statistics
https://github.com/lsxxh/llama-cpp-python#notes-and-limitations
https://github.com/lsxxh/llama-cpp-python#multi-modal-models
llava-v1.5-7bhttps://huggingface.co/mys/ggml_llava-v1.5-7b
llava-v1.6-34bhttps://huggingface.co/cjpais/llava-v1.6-34B-gguf
moondream2https://huggingface.co/vikhyatk/moondream2
nanollavahttps://huggingface.co/abetlen/nanollava-gguf
llama-3-vision-alphahttps://huggingface.co/abetlen/llama-3-vision-alpha-gguf
minicpm-v-2.6https://huggingface.co/openbmb/MiniCPM-V-2_6-gguf
minicpm-v-4.5https://huggingface.co/openbmb/MiniCPM-V-4_5-gguf
minicpm-v-4.6https://huggingface.co/openbmb/MiniCPM-V-4.6-gguf
gemma3https://huggingface.co/unsloth/gemma-3-27b-it-GGUF
gemma4https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF
glm4.1vhttps://huggingface.co/unsloth/GLM-4.1V-9B-Thinking-GGUF
glm4.6vhttps://huggingface.co/unsloth/GLM-4.6V-Flash-GGUF
granite-doclinghttps://huggingface.co/ibm-granite/granite-docling-258M-GGUF
lfm2-vlhttps://huggingface.co/LiquidAI/LFM2-VL-3B-GGUF
lfm2.5-vlhttps://huggingface.co/LiquidAI/LFM2.5-VL-1.6B-GGUF
deepseek-ocrhttps://huggingface.co/JamePeng2023/DeepSeek-OCR-2-GGUF
mineru2.5-prohttps://huggingface.co/JamePeng2023/MinerU2.5-Pro-2605-1.2B-GGUF
paddleocr-vl-1.5https://huggingface.co/JamePeng2023/PaddleOCR-VL-1.5-GGUF
qwen2.5-vlhttps://huggingface.co/unsloth/Qwen2.5-VL-3B-Instruct-GGUF
qwen3-asrhttps://huggingface.co/JamePeng2023/Qwen3-ASR-1.7B-GGUF
qwen3-vlhttps://huggingface.co/unsloth/Qwen3-VL-8B-Thinking-GGUF
qwen3.5https://huggingface.co/unsloth/Qwen3.5-27B-GGUF
qwen3.6https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF
step3-vlhttps://huggingface.co/JamePeng2023/Step3-VL-10B-GGUF
https://github.com/lsxxh/llama-cpp-python#generic-mtmd-chat-handler
https://github.com/lsxxh/llama-cpp-python#chat-template-resolution-order
https://github.com/lsxxh/llama-cpp-python#passing-extra-template-arguments
https://github.com/lsxxh/llama-cpp-python#loading-a-local-image-with-qwen3vlthinkinginstruct
https://github.com/lsxxh/llama-cpp-python#speech-recognition-with-qwen3-asr-speech-to-text
https://github.com/lsxxh/llama-cpp-python#how-it-works
https://github.com/lsxxh/llama-cpp-python#comprehensive-omni-multimodal-example-gemma-4-vision--audio--text
https://github.com/lsxxh/llama-cpp-python#embeddings--reranking-gguf
https://github.com/lsxxh/llama-cpp-python#key-features
https://github.com/lsxxh/llama-cpp-python#support-embeddings--rerank-model
bge-m3-GGUFhttps://huggingface.co/gpustack/bge-m3-GGUF
jina-embeddings-v2-base-zh-GGUFhttps://huggingface.co/gpustack/jina-embeddings-v2-base-zh-GGUF
jina-embeddings-v3-GGUFhttps://huggingface.co/second-state/jina-embeddings-v3-GGUF
bge-reranker-v2-m3-GGUFhttps://huggingface.co/gpustack/bge-reranker-v2-m3-GGUF
Qwen3-Reranker-GGUFhttps://huggingface.co/JamePeng2023/Qwen3-Reranker-GGUF
https://github.com/lsxxh/llama-cpp-python#todojamepeng-needs-more-extensive-testing-with-various-embedding-and-rerank-models-
https://github.com/lsxxh/llama-cpp-python#1-text-embeddings-vector-search
https://github.com/lsxxh/llama-cpp-python#2-reranking-cross-encoder-scoring
https://github.com/lsxxh/llama-cpp-python#3-normalization
https://github.com/lsxxh/llama-cpp-python#using-the-standard-llama-class
https://github.com/lsxxh/llama-cpp-python#docker-image
https://github.com/JamePeng/llama-cpp-python/tree/main/docker#cuda_simplehttps://github.com/JamePeng/llama-cpp-python/tree/main/docker#cuda_simple
https://github.com/lsxxh/llama-cpp-python#openai-compatible-web-server-deprecated
http://localhost:8000/docshttp://localhost:8000/docs
llama_cpp/llama_chat_format.pyhttps://github.com/lsxxh/llama-cpp-python/blob/main/llama_cpp/llama_chat_format.py
https://github.com/lsxxh/llama-cpp-python#web-server-features
Local Copilot replacementhttps://llama-cpp-python.readthedocs.io/en/latest/server/#code-completion
Function Calling supporthttps://llama-cpp-python.readthedocs.io/en/latest/server/#function-calling
Vision API supporthttps://llama-cpp-python.readthedocs.io/en/latest/server/#multimodal-models
Multiple Modelshttps://llama-cpp-python.readthedocs.io/en/latest/server/#configuration-and-multi-model-support
https://github.com/lsxxh/llama-cpp-python#low-level-api
API Referencehttps://llama-cpp-python.readthedocs.io/en/latest/api-reference/#low-level-api
ctypeshttps://docs.python.org/3/library/ctypes.html
llama_cpp/llama_cpp.pyhttps://github.com/abetlen/llama-cpp-python/blob/master/llama_cpp/llama_cpp.py
llama.hhttps://github.com/ggerganov/llama.cpp/blob/master/llama.h
examples folderhttps://github.com/lsxxh/llama-cpp-python/blob/main/examples/low_level_api
https://github.com/lsxxh/llama-cpp-python#documentation
https://llama-cpp-python.readthedocs.io/https://llama-cpp-python.readthedocs.io/
https://github.com/lsxxh/llama-cpp-python#development
https://github.com/lsxxh/llama-cpp-python#faq
https://github.com/lsxxh/llama-cpp-python#are-there-pre-built-binaries--binary-wheels-available
https://github.com/lsxxh/llama-cpp-python#how-does-this-compare-to-other-python-bindings-of-llamacpp
https://github.com/lsxxh/llama-cpp-python#oserror-libcudartsoxxcudart64_xxdll-cannot-open-shared-object-file-no-such-file-or-directory
https://github.com/lsxxh/llama-cpp-python#filenotfounderror-could-not-find-module-like-ggmldll-ggml-cpudll-ggml-cudadll
https://github.com/lsxxh/llama-cpp-python#why-are-libraries-compiled-by-other-authors-only-around-100mb-while-your-pre-compiled-versions-are-300mb-or-larger
https://github.com/lsxxh/llama-cpp-python#quick-tips-for-developuser-continuously-updated
https://github.com/lsxxh/llama-cpp-python#any-suggestions-contributions-and-modifications-to-this-package-will-be-directed-toward-building-a-user-friendly-efficient-and-secure-python-library
https://github.com/lsxxh/llama-cpp-python#license
github.com/JamePeng/llama-cpp-python/wikihttps://github.com/JamePeng/llama-cpp-python/wiki
Readmehttps://github.com/lsxxh/llama-cpp-python#readme-ov-file
Licensehttps://github.com/lsxxh/llama-cpp-python#License-1-ov-file
Activityhttps://github.com/lsxxh/llama-cpp-python/activity
0 forkshttps://github.com/lsxxh/llama-cpp-python/forks
Report repositoryhttps://github.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2Flsxxh%2Fllama-cpp-python&report=lsxxh+%28user%29
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.