Reporium
GraphWikiTaxonomyStacksInsightsTrendsArchitectureAI-NativeFAQ
Ask anything about the repo library…
Loading repo…
←Library/ggml
Library/ggmlForked

ggml-org/ggml

ggml

Tensor library for machine learning

View on GitHub↗Upstream ggml-org/ggml↗

Builder

ggml-org

ggml-org

ggml-org • individual

Stars

14,727

Using upstream star count

Forks

1,638

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Sep 18, 2022

Project creation date

README Summary

[Roadmap](https://github.com/users/ggerganov/projects/7) / [Manifesto](https://github.com/ggerganov/llama.cpp/discussions/205)

Community Evaluation

Loading…

AI Dev Skills

Unmapped

CPU OptimizationCross-platform DevelopmentHardware AccelerationLow-level Machine LearningMemory ManagementNumerical ComputingPerformance EngineeringQuantization TechniquesSIMD ProgrammingTensor Operations

Tags

CPU OptimizationCross-platform DevelopmentHardware AccelerationLow-level Machine LearningMemory ManagementNumerical ComputingPerformance EngineeringQuantization TechniquesSIMD ProgrammingTensor OperationsC++ForkedGPU / CUDAHuggingFaceMachine LearningMobileOpenAIPythonQuantizationRoadmapSpeech to TextTransformersTutorialllama.cpp

Taxonomy

AI Trends

On-device AIEdge ComputingModel QuantizationEfficient InferenceHardware Optimization

category

Foundation ModelsInference & ServingGenerative MediaLearning Resources

Deployment Context

Edge/MobileSelf-hostedOn-premiseCross-platform

Modalities

TextAudio

Skill Areas

Tensor OperationsCPU OptimizationLow-level Machine LearningMemory ManagementSIMD ProgrammingCross-platform DevelopmentPerformance EngineeringQuantization TechniquesHardware AccelerationNumerical Computing

tag

C++ForkedGPU / CUDAHuggingFaceMachine LearningMobileOpenAIPythonQuantizationRoadmapSpeech to TextTransformersTutorialllama.cpp

Use Cases

Large Language Model InferenceOn-device AI ApplicationsCPU-based Model DeploymentResource-constrained AI SystemsCross-platform ML Inference

Recent Activity

Updated 3 months ago

7 Days

0

30 Days

0

90 Days

0

support permuted, remove check s0/s10 (llama/19889)

Neo Zhang • Feb 27, 2026

4a7c752

replace the magic nunber 768 by max work group size to support iGPU (llama/19920)

Neo Zhang • Feb 27, 2026

19a1def

ggml-zendnn: update code for latest ZenDNN API (llama/19923)

Vishal Singh • Feb 27, 2026

de28b82

Quality

production
Quality
high
Maturity
production

Categories

Inference & ServingPrimaryLearning ResourcesFoundation ModelsGenerative MediaEdge & Mobile AIOther AI / ML

PM Skills

Cost & EfficiencyUser Experience

Languages

C++100.0%

Timeline

Project created
Sep 18, 2022
Forked
Mar 13, 2026
Your last push
3 months ago
Upstream last push
18 days ago
Tracked since
Feb 27, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…