jdestevezcastillo commited on
Commit
dca2dd5
·
verified ·
1 Parent(s): fca8122

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +68 -7
README.md CHANGED
@@ -1,10 +1,71 @@
1
  ---
2
- title: README
3
- emoji: 📚
4
- colorFrom: green
5
- colorTo: purple
6
- sdk: static
7
- pinned: false
 
 
 
 
 
 
8
  ---
9
 
10
- Edit this `README.md` markdown file to author your organization card.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ title: "AI Performance Engineering Community"
3
+ emoji: "⚙️"
4
+ colorFrom: "blue"
5
+ colorTo: "purple"
6
+ sdk: "static"
7
+ short_description: "AI Performance Engineering: benchmarks, tooling & tips"
8
+ tags:
9
+ - performance
10
+ - llm
11
+ - benchmarking
12
+ - optimization
13
+ - inference
14
  ---
15
 
16
+ # AI Performance Engineering Community
17
+
18
+ Welcome to the **AI Performance Engineering Community**, a collaborative space for anyone working on or curious about performance engineering in the age of large-scale AI systems.
19
+
20
+ This community brings together:
21
+ - **Performance engineers** transitioning into AI workloads
22
+ - **LLM practitioners** who need to measure, optimize, and scale models
23
+ - **Researchers** exploring efficiency techniques
24
+ - **Beginners** who want hands-on guidance
25
+ - **Experts** who want to share tools, insights, and benchmarks
26
+
27
+ ## 🎯 Purpose
28
+ The goal of this group is to build a shared knowledge base around:
29
+ - Performance testing of AI models (LLMs, diffusion models, multimodal models)
30
+ - Benchmarking methodologies and tools
31
+ - Profiling techniques for GPU, CPU, memory, and distributed systems
32
+ - Energy and cost efficiency
33
+ - Latency, throughput, and scalability patterns
34
+ - Observability for AI workloads
35
+ - Real-world test results and reproducible experiments
36
+
37
+ ## 🧰 What You Can Share
38
+ - Scripts, datasets, and reproducible benchmark setups
39
+ - Test results across different hardware and model sizes
40
+ - Tips and challenges when scaling models
41
+ - Profiling and instrumentation tools
42
+ - Guides for newcomers
43
+ - Research, papers, and best practices
44
+
45
+ ## 🤝 Community Principles
46
+ 1. **Open collaboration** over gatekeeping
47
+ 2. **Reproducibility** over hand-wavy claims
48
+ 3. **Respectful discussion**, beginner-friendly environment
49
+ 4. **Practicality first**, theory second
50
+ 5. **Continuous learning** in an industry that moves fast
51
+
52
+ ## 🚀 Who Should Join?
53
+ - Performance engineers exploring AI workloads
54
+ - ML engineers who want to optimize inference or training
55
+ - DevOps/SRE/platform engineers dealing with AI pipelines
56
+ - Students and researchers
57
+ - Anyone interested in making AI systems faster, cheaper, and more efficient
58
+
59
+ ## 📚 Roadmap (Community-Guided)
60
+ - Curated list of open-source AI performance tools
61
+ - Shared benchmarking suites
62
+ - “Ask the experts” threads
63
+ - Regular community challenges
64
+ - Tutorials on evaluation, profiling, and optimization
65
+ - Hardware performance comparison repository
66
+
67
+ ## 💬 Get Involved
68
+ Post your tests, tools, questions, insights, failures, and victories.
69
+ Every contribution helps build the first open community dedicated fully to **AI performance engineering**.
70
+
71
+ Let’s make AI systems faster, more efficient, and more accessible—together.