← νŠΈλ Œλ”©

Tangerine IndexλŠ” ChatGPT 이후 λ‚˜μ˜¨ ν”„λ‘œλ•νŠΈμ™€ μ‚¬λžŒλ“€μ˜ λ°˜μ‘μ„ μ‹£μŠ΅λ‹ˆλ‹€.

whisper-turbo

github.com

Cross-Platform, GPU Accelerated Whisper 🏎️

λ°μŠ€ν¬ν†±μ˜€ν”ˆμ†ŒμŠ€

github.com λ°©λ¬Έμ™ΈλΆ€ μ‚¬μ΄νŠΈGitHub1,795 μŠ€νƒ€μ™ΈλΆ€ μ‚¬μ΄νŠΈ

λ°˜μ‘ (1)

λΉ„μŠ·ν•œ ν”„λ‘œλ•νŠΈ

μ„€λͺ…이 λΉ„μŠ·ν•œ 순

  1. stable-fast

    https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

    github.comλΌμ΄λΈŒλŸ¬λ¦¬μ˜€ν”ˆμ†ŒμŠ€μ΅œκ·Ό λ°˜μ‘

    Hacker News
    λ°˜μ‘ μ—†μŒ
    GitHub
    μŠ€νƒ€ 1,306

  2. CubeCL

    Multi-Platform GPU Computing

    github.comμ˜€ν”ˆμ†ŒμŠ€λ°˜μ‘ 2개졜근 λ°˜μ‘

    Hacker News
    10점
    GitHub
    μŠ€νƒ€ 2,490

  3. whisper-plus

    WhisperPlus: Faster, Smarter, and More Capable πŸš€

    github.comμ˜€ν”ˆμ†ŒμŠ€μ΅œκ·Ό λ°˜μ‘

    Hacker News
    λ°˜μ‘ μ—†μŒ
    GitHub
    μŠ€νƒ€ 1,946

  4. tachyon

    Modular ZK(Zero Knowledge) backend accelerated by GPU

    github.comμ˜€ν”ˆμ†ŒμŠ€μ΅œκ·Ό λ°˜μ‘

    Hacker News
    λ°˜μ‘ μ—†μŒ
    GitHub
    μŠ€νƒ€ 7,642

  5. Local fine tuning for Mistral and SDXL, GPU mem/latency optimization

    100% bootstrapped new startup.

    docs.helix.ml졜근 λ°˜μ‘

    Hacker News
    36점
    GitHub
    λ°˜μ‘ μ—†μŒ