Pinchflat

Insanely Fast LLM Inference with this Stack

Media Tasks
Actions

Raw Attributes

Source: Code to the Moon
  • media_id: oTMX_4jfRy8
  • duration_seconds: 642
  • predicted_media_filepath: /downloads/chris/tubes/Code to the Moon_[UCjREVt2ZJU8ql-NC9Gu-TJw]/Season 2025/s2025e092300_Insanely Fast LLM Inference with this Stack.mp4
  • short_form_content: false
  • upload_date_index: 99
  • nfo_filepath: /downloads/chris/tubes/Code to the Moon_[UCjREVt2ZJU8ql-NC9Gu-TJw]/Season 2025/s2025e092399_Insanely Fast LLM Inference with this Stack.nfo
  • media_filepath: /downloads/chris/tubes/Code to the Moon_[UCjREVt2ZJU8ql-NC9Gu-TJw]/Season 2025/s2025e092399_Insanely Fast LLM Inference with this Stack.mp4
  • description: A walkthrough of some of the options developers are faced with when building applications that leverage LLMs. Includes self-hosting vs using inference providers, which inference providers stand out from the rest, and approaches to testing prompt/model/provider efficacy. Check out the code for the simple chatbot CLI here: https://github.com/MoonKraken/youtube/tree/main/hf_cli_chatbot Keyboard: Glove80 - https://bit.ly/3EKyn7X Camera: Canon EOS R8 https://amzn.to/4gSpivt Monitor: Dell U4914DW 49in https://amzn.to/3MJV1jx Microphone: Sennheiser 416 https://amzn.to/3Fkti60 Microphone Interface: Focusrite Clarett+ 2Pre https://amzn.to/3J5dy7S Tripod: JOBY GorillaPod 5K https://amzn.to/3JaPxMA Mouse: Razer DeathAdder https://amzn.to/3J9fYCf Computer: 2021 Macbook Pro https://amzn.to/3J7FXtW Lens: Canon RF50mm F 1.2L USM https://amzn.to/3qeJrX6 Caffeine: High Brew Cold Brew Coffee https://amzn.to/3hXyx0q More Caffeine: Monster Energy Juice, Pipeline Punch https://amzn.to/3Czmfox Building A Second Brain book: https://amzn.to/3cIShWf
  • updated_at: 2025-09-24T10:24:02Z
  • id: 1137792
  • media_size_bytes: 36494676
  • inserted_at: 2025-09-24T10:23:38Z
  • media_redownloaded_at:
  • prevent_culling: false
  • source_id: 18
  • original_url: https://www.youtube.com/watch?v=oTMX_4jfRy8
  • uuid: 22434971-8511-4982-ab7d-24e80d537499
  • matching_search_term:
  • metadata_filepath: /downloads/chris/tubes/Code to the Moon_[UCjREVt2ZJU8ql-NC9Gu-TJw]/Season 2025/s2025e092399_Insanely Fast LLM Inference with this Stack.info.json
  • uploaded_at: 2025-09-23T14:01:32Z
  • thumbnail_filepath: /downloads/chris/tubes/Code to the Moon_[UCjREVt2ZJU8ql-NC9Gu-TJw]/Season 2025/s2025e092399_Insanely Fast LLM Inference with this Stack-thumb.jpg
  • prevent_download: false
  • tasks:
  • title: Insanely Fast LLM Inference with this Stack
  • last_error:
  • culled_at:
  • subtitle_filepaths:
  • media_downloaded_at: 2025-09-24T10:23:58Z
  • livestream: false
  • playlist_index: 1

Nothing Here!