8000 abetlen llama-cpp-python · Discussions · GitHub
[go: up one dir, main page]
Skip to content

abetlen llama-cpp-python Discussions

Clear
Sort by: Latest activity
Latest activity
Date created
Top: Past day
Top: Past week
Top: Past month
Top: Past year
Top: All

Filter by label

Use alt + click/return to exclude labels.

Discussions

  • You must be logged in to vote

    Worse speed and GPU load than pure llama-cpp

    Mushoz asked Nov 14, 2024 in Q&A · Answered
    @Mushoz @ExtReMLapin
    @gl2007
    @Mushoz @ExtReMLapin
    @gl2007
    4
  • You must be logged in to vote

    Running multiple tiny models in parallel on a single GPU

    abarai-lanl asked May 11, 2025 in Q&A · Unanswered
    @abarai-lanl @onestardao
    @abarai-lanl @onestardao
    3
  • You must be logged in to vote

    Api/generate endpoint

    gl2007 asked Feb 5, 2025 in Q&A · Unanswered
    @gl2007 @onestardao
    @gl2007 @onestardao
    1
  • You must be logged in to vote

    OSError('exception: access violation reading 0x0000000000000000')

    OreNot started Feb 5, 2025 in General
    @OreNot @onestardao
    @OreNot @onestardao
    1
  • You must be logged in to vote

    where is the UI file of the server locate in this python binding llama-cpp-python

    heylobc started Feb 8, 2025 in General
    @heylobc @onestardao
    @heylobc @onestardao
    1
  • You must be logged in to vote

    Getting Embedding from CLIP model

    lelefontaa asked Feb 18, 2025 in Q&A · Unanswered
    @lelefontaa @onestardao
    10BC0
    @lelefontaa @onestardao
    1
  • You must be logged in to vote

    Segmentation fault on tensor conversion

    devashishraj asked Feb 15, 2025 in Q&A · Unanswered
    @devashishraj @onestardao
    @devashishraj @onestardao
    1
  • You must be logged in to vote

    Is the bug template accurate when it says "there are no tagged versions as of now"?

    nchammas asked Apr 10, 2025 in Q&A · Unanswered
    @nchammas @onestardao
    @nchammas @onestardao
    1
  • You must be logged in to vote

    Throughputs of Long Sequences #12608

    simmonssong asked Mar 27, 2025 in Q&A · Unanswered
    @simmonssong @onestardao
    @simmonssong @onestardao
    1
  • You must be logged in to vote

    Super simple Python connectors for llama.cpp, including vision models (Gemma 3, Qwen2-VL)

    fidecastro started Mar 19, 2025 in Show and tell
    @fidecastro @onestardao
    @fidecastro @onestardao
    1
  • You must be logged in to vote

    Hope to support dynamically loaded libraries ggml-base.so

    yigekuyou started May 13, 2025 in Ideas
    @yigekuyou @onestardao
    @yigekuyou @onestardao
    1
  • You must be logged in to vote

    [Guide]: How to ACTUALLY get it installed in (Fedora 42) linux

    thedarkbird started Jul 18, 2025 in General
    @thedarkbird @onestardao
    @thedarkbird @onestardao
    1
  • You must be logged in to vote

    Best way to apply chat templates locally

    bwilkie asked Feb 10, 2025 in Q&A · Unanswered
    @bwilkie @rrrusst
    @bwilkie @rrrusst
    1
  • You must be logged in to vote

    How do I get <think> from e.g. Qwen 3 prompt with /think adds a paragraph with think.

    LaKanDoR started May 2, 2025 in General
    @LaKanDoR
    @LaKanDoR
    1
  • You must be logged in to vote

    Delay between prompt submission and first token generation with longer prompts

    jhthompson12 asked Dec 26, 2023 in Q&A · Unanswered
    @jhthompson12 @hule369
    @AdityaKulshrestha
    @jhthompson12 @hule369
    @AdityaKulshrestha
    4
  • You must be logged in to vote

    Use model for multiple user sessions

    riebers-m started Sep 4, 2024 in General
    @riebers-m @ExtReMLapin
    @PokeLu
    @riebers-m @ExtReMLapin
    @PokeLu
    9
  • You must be logged in to vote

    THIS is how to Get CUDA Working with llama-cpp-python!

    PasiKoodaa started Feb 9, 2025 in General · Closed
    @PasiKoodaa
    @PasiKoodaa
    0
  • You must be logged in to vote

    How to make it work with CUDA-support?

    itinance asked Aug 18, 2024 in Q&A · Unanswered
    @itinance @jason-kane
    @laelhalawani
    @itinance @jason-kane
    @laelhalawani
    2
    • 0