Notes

[louisgv]

CUDA supports:

https://github.com/kimlimjustin/xplorer/blob/master/src/Service/app.ts https://github.com/launchbadge/sqlx https://github.com/Jimver/cuda-toolkit https://github.com/LLukas22/llm-rs-python/blob/main/.github/workflows/CI-CuBLAS.yml

CI/headless:

https://dev.to/chenhunghan/offline-ai-on-github-actions-38a1 https://github.com/chenhunghan/ialacol/tree/main

Inference:

https://github.com/rustformers/llm/blob/main/crates/llm-base/src/inference_session.rs#L440-L441 https://github.com/grantslatton/llama.cpp/commit/007e26a99d485007f724957fa8545331ab8d50c3

Learning:

https://e2eml.school/numpy_resources.html https://e2eml.school/how_backpropagation_works.html https://e2eml.school/transformers.html

RWKV:

https://github.com/josephrocca/rwkv-v4-web/tree/main https://github.com/BlinkDL/RWKV-LM

P2P:

https://github.com/bigscience-workshop/petals#readme

SD:

https://github.com/kohya-ss/sd-scripts

misc: https://github.com/salesforce/CodeGen https://github.com/turboderp/exllama/tree/master https://github.com/triton-inference-server/backend/blob/main/docs/backend_platform_support_matrix.md

[louisgv]

https://github.com/TabbyML/tabby/blob/main/clients/tabby-agent/src/Auth.ts

[louisgv]

Dev tool/vscode extension: https://github.com/ggml-org/p1/discussions/1

[louisgv]

https://dholmes.co.uk/blog/5-approaches-to-solve-llm-token-limits/

[louisgv]

On tokenization:

https://rentry.co/ALLMRR

https://github.com/alasdairforsythe/tokenmonster

[louisgv]

On App bundling:

https://tauri.app/v1/guides/distribution/updater/#static-json-file

https://developer.apple.com/documentation/security/notarizing_macos_software_before_distribution/customizing_the_notarization_workflow

[louisgv]

https://learn.microsoft.com/en-us/semantic-kernel/when-to-use-ai/schillace-laws

[louisgv]

On agent:

https://github.com/eumemic/ai-legion/tree/master

[louisgv]

On Llama2:

https://github.com/huggingface/text-generation-inference/releases

https://github.com/facebookresearch/llama-recipes/

https://github.com/facebookresearch/llama/tree/main

https://huggingface.co/docs/transformers/model_doc/llama2

https://github.com/google/sentencepiece