Hacker News
- Fast and Portable Llama2 Inference on the Heterogeneous Edge https://www.secondstate.io/articles/fast-llm-inference/ 98 comments
Linking pages
- Getting Started with Mistral-7b-Instruct-v0.1 https://www.secondstate.io/articles/mistral-7b-instruct-v0.1/ 54 comments
- Mathstral: A New LLM that is Good at Math Reasoning https://www.secondstate.io/articles/mathstral/ 32 comments
- Getting Started with Orca-2-13B https://www.secondstate.io/articles/orca-2-13b/ 17 comments
- Getting Started with StableLM-2-Zephyr-1.6B https://www.secondstate.io/articles/stablelm-2-zephyr-1.6b/ 5 comments
- Getting Started with Mixtral-8x7B https://www.secondstate.io/articles/mixtral-8-7b/ 3 comments
- Getting Started with Nous-Hermes-2-Mixtral-8x7B SFT https://www.secondstate.io/articles/nous-hermes-2-mixtral-8x7b-sft/ 3 comments
- Getting Started with Starling-LM-7B-alpha https://www.secondstate.io/articles/starling-lm-7b-alpha/ 1 comment
- Getting Started with CALM2-7B-Chat https://www.secondstate.io/articles/calm2-7b-chat/ 1 comment
- Getting Started with Qwen1.5-0.5B-Chat https://www.secondstate.io/articles/qwen1.5-0.5b-chat/ 1 comment
- Getting Started with Gemma-7b-it https://www.secondstate.io/articles/gemma-7b-it/ 1 comment
- Getting Started with Qwen1.5-72B-Chat https://www.secondstate.io/articles/qwen1.5-72b-chat/ 1 comment
- Getting Started with Llama 3.1 https://www.secondstate.io/articles/llama-31-8b/ 1 comment
- Getting Started with Phi-3.5-mini-instruct https://www.secondstate.io/articles/phi-3-5-mini-instruct/ 1 comment
- Getting started with Qwen2.5-14B https://www.secondstate.io/articles/qwen25/ 1 comment
- Getting Started with Dolphin-2.2-yi-34b https://www.secondstate.io/articles/dolphin-2.2-yi-34b/ 0 comments
- Getting Started with SOLAR-10.7B-Instruct-v1.0 https://www.secondstate.io/articles/solar-10.7b-instruct-v1.0/ 0 comments
Linked pages
- GitHub - ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++ https://github.com/ggerganov/llama.cpp 286 comments
- GitHub - WasmEdge/WasmEdge: WasmEdge is a lightweight, high-performance, and extensible WebAssembly runtime for cloud native, edge, and decentralized applications. It powers serverless apps, embedded functions, microservices, smart contracts, and IoT devices. https://github.com/WasmEdge/WasmEdge 33 comments
- https://blog.stackademic.com/why-did-elon-musk-say-that-rust-is-the-language-of-agi-eb36303ce341 15 comments
- Modular: How Mojoð¥ gets a 35,000x speedup over Python â Part 1 https://www.modular.com/blog/how-mojo-gets-a-35-000x-speedup-over-python-part-1 7 comments
- https://en.wikipedia.org/wiki/chris_lattner 4 comments
- Flows.network https://flows.network/ 3 comments
- Wasm as the runtime for LLMs and AGI https://www.secondstate.io/articles/wasm-runtime-agi/ 2 comments
- https://github.com/philpax/ggml/blob/gguf-spec/docs/gguf.md 1 comment
- https://github.com/second-state/WasmEdge-WASINN-examples/tree/master/wasmedge-ggml-llama-interactive 1 comment
- MediaPipe | Google Developers https://developers.google.com/mediapipe 0 comments
- How do I create a GGUF model file? https://www.secondstate.io/articles/convert-pytorch-to-gguf/ 0 comments
Related searches:
Search whole site: site:secondstate.io
Search title: Fast and Portable Llama2 Inference on the Heterogeneous Edge
See how to search.