Defeating Nondeterminism in LLM Inference

thinkingmachines.ai/blog/defeating-nondeterminism-in-llm-inference/

Difference Array | Range update query in O(1) - GeeksforGeeks

www.geeksforgeeks.org/difference-array-range-update-query-o1/

Enterprise h2oGPTe

h2ogpte.genai.h2o.ai/feedback

Hermes 3 Technical Report - 2408.11857v1.pdf

arxiv.org/pdf/2408.11857

NousResearch/Hermes-3-Llama-3.2-3B · Hugging Face

huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B

2410.23261v1.pdf

arxiv.org/pdf/2410.23261

2304.12206v2.pdf

arxiv.org/pdf/2304.12206

Mat’s Blog - CUDA MODE - Accelerate your code with massively parallel programming plus some other tricks

blog.matdmiller.com/posts/2024-02-15_custom_cuda_kernel_intro_and_benchmarks/notebook.html

Chroma - LlamaIndex

docs.llamaindex.ai/en/stable/examples/vector_stores/ChromaIndexDemo/

FineWeb: decanting the web for the finest text data at scale

huggingfacefw-blogpost-fineweb-v1.static.hf.space/dist/index.html

What We Learned from a Year of Building with LLMs (Part I)

www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms-part-i/

2402.00530v1.pdf

arxiv.org/pdf/2402.00530v1

Your Work | Kaggle

www.kaggle.com/work/collections/14111779

Efficient NLP Model Finetuning via Multistage Data Filtering - 0455.pdf

www.ijcai.org/proceedings/2023/0455.pdf

2405.00732v1.pdf

arxiv.org/pdf/2405.00732

RoFormer - 2104.09864v5.pdf

arxiv.org/pdf/2104.09864

Transformer Architecture: The Positional Encoding - Amirhossein Kazemnejad's Blog

kazemnejad.com/blog/transformer_architecture_positional_encoding/

Notion – The all-in-one workspace for your notes, tasks, wikis, and databases.

yaofu.notion.site/Towards-100x-Speedup-Full-Stack-Transformer-Inference-Optimization-43124c3688e14cffaf2f1d6cbdf26c6c

arxiv.org/pdf/2403.19887v1

Musings on Building a Generative AI Product

www.linkedin.com/blog/engineering/generative-ai/musings-on-building-a-generative-ai-product

2404.14619v1.pdf

arxiv.org/pdf/2404.14619

2404.02258.pdf

arxiv.org/pdf/2404.02258.pdf

Answer.AI - A few tips for working on high-surface-area problems

www.answer.ai/posts/2024-04-12-tips.html

2203.11171.pdf

arxiv.org/pdf/2203.11171.pdf

2404.07965.pdf

arxiv.org/pdf/2404.07965.pdf

2403.07815.pdf

arxiv.org/pdf/2403.07815.pdf

2403.17297.pdf

arxiv.org/pdf/2403.17297.pdf

2403.08763.pdf

arxiv.org/pdf/2403.08763.pdf

2403.13372.pdf

arxiv.org/pdf/2403.13372.pdf

Keras documentation: Video Classification with a CNN-RNN Architecture

keras.io/examples/vision/video_classification/