karpathy/llama2.c
llama2.c
Inference Llama 2 in one file of pure C
Builder
karpathy
karpathy • individual
Stars
19,347
Using upstream star count
Forks
2,485
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Jul 23, 2023
Project creation date
README Summary
A minimal implementation of Llama 2 inference written in pure C, contained in a single file with no dependencies. The project aims to demonstrate how to run Llama 2 models efficiently using only standard C libraries. It provides a lightweight alternative to heavy Python frameworks for running Llama 2 inference.
AI Dev Skills
Unmapped
Transformer ArchitectureLanguage Model InferenceModel OptimizationSystems ProgrammingNeural Network ImplementationQuantization TechniquesMemory Management
Tags
Transformer ArchitectureLanguage Model InferenceModel OptimizationSystems ProgrammingNeural Network ImplementationQuantization TechniquesMemory ManagementMinimal AI InfrastructureEdge/MobileOn-premiseEducational AI ImplementationTextIoTSmall Language ModelsEdge ComputingMinimal AI InferenceSelf-hostedResearch PrototypingOn-device AIEducationEmbedded Language ProcessingLow-resource Text GenerationEmbedded SystemsC
Taxonomy
Deployment Context
Industries
Modalities
Skill Areas
Recent Activity
Updated 1 years ago
7 Days
0
30 Days
0
90 Days
0
Quality
prototype- Quality
- medium
- Maturity
- prototype
Categories
Other AI / MLPrimaryInference & ServingML Platform & InfrastructureEdge & Mobile AISearch & KnowledgeDev Tools & AutomationLearning ResourcesFoundation Models
PM Skills
Developer Platform
Languages
C100.0%
Timeline
- Project created
- Jul 23, 2023
- Forked
- Mar 13, 2026
- Your last push
- 1 years ago
- Upstream last push
- 1 years ago
- Tracked since
- Aug 6, 2024
Similar Repos
pgvector cosine similarity · $0
Loading…