How liguodongiot/llm-action works
This repository is an educational collection of LLM and AI engineering examples, not one integrated runtime. The README organizes tutorials around training, inference, compression, evaluation, data engineering, applications, algorithms, and domestic-hardware adaptation; the tree contains corresponding scripts. The principal user workflow is to choose a tutorial area and run its example, with training, serving, and performance measurement as distinct domain stages. The graph groups these capabilities rather than implying a shared application pipeline. Connections are limited to README-documented areas and excerpted behavior; many indexed scripts were not sampled.
Main entry points: llm-inference LLM Serving · llm-performance Inference Benchmarks · mindsporelite-inference.py MindSpore Lite · firefly_lambada_1w_stat_token.py LAMBADA Evaluation
Components 19
Training
- LLM Training
llm-train - Efficient Tuning
llm-train/peft - Distributed Training
llm-train/pytorch/distribution - AI Framework Demos
ai-framework
Inference
- LLM Serving
llm-inference - MindSpore Lite
llm-inference/ascend/mindformers/mindsporelite-inference.py - Web API
llm-inference/web/fastapi/llm-qwen-mindspore-lite.py - vLLM Client
llm-inference/vllm/api_client.py - Triton Client
llm-inference/triton/resnet50/client.py
Compression
- QAT Workflows
llm-compression/quantization/llm-qat
Evaluation
- Inference Benchmarks
llm-eval/llm-performance - GPU Monitoring
llm-eval/llm-performance/stat_gpu_memory.py - Profiling Tools
llm-tools/base-profiler.py - LAMBADA Evaluation
llm-inference/faster-transformer/bloom/firefly_lambada_1w_stat_token.py
Data and Ecosystem
- SFT Templates
llm-data-engineering/sft-dataset - Model Algorithms
llm-algo - LLM Applications
llm-application/langchain/serve.py - Hardware Adaptation
llm-localization/ascend
Other components
- Engineer
Connections 18
- Engineer → LLM Training: explores tutorials
README.md - Engineer → LLM Serving: explores tutorials
README.md - Engineer → QAT Workflows: explores tutorials
README.md - Engineer → Inference Benchmarks: explores tutorials
README.md - Engineer → SFT Templates: explores tutorials
README.md - Engineer → LLM Applications: explores tutorials
README.md - Engineer → Model Algorithms: explores tutorials
README.md - Engineer → Hardware Adaptation: explores tutorials
README.md - Engineer → Efficient Tuning: explores tutorials
README.md - Engineer → Distributed Training: explores tutorials
README.md - Engineer → AI Framework Demos: explores tutorials
README.md - LLM Serving → MindSpore Lite: includes example
README.md - LLM Serving → vLLM Client: includes client
README.md - LLM Serving → Triton Client: includes client
- MindSpore Lite → Web API: serves through
llm-inference/web/fastapi/llm-qwen-mindspore-lite.py - Inference Benchmarks → GPU Monitoring: includes monitoring
README.md - Inference Benchmarks → Profiling Tools: includes profiling
- LAMBADA Evaluation → Inference Benchmarks: measures inference