Posts on Generative AI | learner | Winner of Huggingface / Cohere / Machine Hack / Adobe global hackathons🏅 | Prompt engineer🦜 | Creator of Shaheen 🦅, Baith-al-suroor ,meme world 🤗.
This is detailed guide to calculate GPU Memory 💾 requirement for serving LLMs. Ps - it doesn't take context length into consideration Website 📖- https://lnkd.in/gf7YzqJt
Hello, How are do? Is to inference model? And... serves as a reference for fine tuning?
Graphics/Engine Programmer @The GD Studio - Specialized in Custom Game Engines | 10+ years doing gamedev | Helping people create and understand rendering
How do you write Shaders optimally? Compared to CPU code, it’s fairly easy to know what should and shouldn’t be done But there is way less knowladge about the GPU and shaders Everything from: → Compiling → Data packing → Cache friendly-ness Those are some of the key things I wanted to know about And that’s why I made the following video Covering my 10 best practices with writing shaders And what I would've liked to learn sooner Watch here: https://lnkd.in/dSGnsKsW
Become a pro #CUDA bug hunter! Learn how to debug: ✅ Memory initialization ✅ Thread synchronization with NVIDIA Compute Sanitizer. Try samples: https://lnkd.in/eixc9nAw 💻 Start learning: ➡️
Become a pro #CUDA bug hunter! Learn how to debug: ✅ Memory initialization ✅ Thread synchronization with NVIDIA Compute Sanitizer. Try samples: https://lnkd.in/gSWTmp3w 💻 Start learning: ➡️
Very useful tool - Calculates how much GPU memory you need and how much token/s you can get for any LLM & GPU/CPU. Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization https://lnkd.in/gn9qbbS2 #llm
Become a pro #CUDA bug hunter! Learn how to debug: ✅ Memory initialization ✅ Thread synchronization with NVIDIA Compute Sanitizer. Try samples: https://lnkd.in/gnRKNHhf 💻 Start learning: ➡️
Become a pro #CUDA bug hunter! Learn how to debug: ✅ Memory initialization ✅ Thread synchronization with NVIDIA Compute Sanitizer. Try samples: https://lnkd.in/eEdamHpA 💻 Start learning: ➡️
Become a pro #CUDA bug hunter! Learn how to debug: ✅ Memory initialization ✅ Thread synchronization with NVIDIA Compute Sanitizer. Try samples: https://lnkd.in/dtnGPvM3 💻 Start learning: ➡️
Become a pro #CUDA bug hunter! Learn how to debug: ✅ Memory initialization ✅ Thread synchronization with NVIDIA Compute Sanitizer. Try samples: https://lnkd.in/gvppss58 💻 Start learning: ➡️
Become a pro #CUDA bug hunter! Learn how to debug: ✅ Memory initialization ✅ Thread synchronization with NVIDIA Compute Sanitizer. Try samples: https://lnkd.in/gvppss58 💻 Start learning: ➡️
Become a pro #CUDA bug hunter! Learn how to debug: ✅ Memory initialization ✅ Thread synchronization with NVIDIA Compute Sanitizer. Try samples: https://lnkd.in/gNr_wBJD 💻 Start learning: ➡️
Data Engineer | Informatica
7moThanks for sharing! We can determine chunk sizes as per requirement from this right? After putting the context length also in the numerator...