Skip to content

Issues: ggml-org/llama.cpp

changelog : libllama API
#9289 opened Sep 3, 2024 by ggerganov
Open 9
changelog : llama-server REST API
#9291 opened Sep 3, 2024 by ggerganov
Open 15
tutorials : list for llama.cpp
#13523 opened May 14, 2025 by ggerganov
Open 3
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
15 Open 38 Closed
15 Open 38 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Research: How to integrate VITA 1.5 for multi-modal GGUF deployment? research 🔬
#13520 opened May 14, 2025 by jordanqi
5 tasks
ggml-quants : weighted rounding algorithms with cumulative search generation quality Quality of model output ggml changes relating to the ggml tensor library for machine learning Less than 4 bits Efforts related to viable quantized models using <4 bits research 🔬 Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level Tensor Encoding Scheme https://github.com/ggerganov/llama.cpp/wiki/Tensor-Encoding-Schemes
#12557 opened Mar 25, 2025 by compilade • Draft
20
ggml : add ANE backend help wanted Extra attention is needed research 🔬 roadmap Part of a roadmap project
#10453 opened Nov 22, 2024 by ggerganov
12
ggml : add WebGPU backend help wanted Extra attention is needed research 🔬 roadmap Part of a roadmap project
#7773 opened Jun 5, 2024 by ggerganov
15
ggml : add DirectML backend help wanted Extra attention is needed research 🔬 roadmap Part of a roadmap project
#7772 opened Jun 5, 2024 by ggerganov
10
llama : support Mamba-2 model Model specific research 🔬 roadmap Part of a roadmap project
#7727 opened Jun 4, 2024 by ggerganov
1
1
metal : compile-time kernel args and params performance Speed related topics research 🔬 roadmap Part of a roadmap project
#4085 opened Nov 15, 2023 by ggerganov
4
Layer skipping/self-speculation demo demo Demonstrate some concept or idea, not intended to be merged research 🔬
#3565 opened Oct 10, 2023 by KerfuffleV2 • Draft
41
llama : combined beam search + grammar sampling strategy generation quality Quality of model output good first issue Good for newcomers research 🔬 roadmap Part of a roadmap project
#2923 opened Aug 31, 2023 by ggerganov
13
mpi : attempt inference of 65B LLaMA on a cluster of Raspberry Pis hardware Hardware related help wanted Extra attention is needed research 🔬 🦙. llama
#2164 opened Jul 10, 2023 by ggerganov
54
[IDEA] Global token enhancement/depression help wanted Extra attention is needed research 🔬
#1865 opened Jun 15, 2023 by elephantpanda
1
Added Arbitrary mixed quantization Less than 4 bits Efforts related to viable quantized models using <4 bits research 🔬
#1834 opened Jun 13, 2023 by Milkdrop Loading…
6
[Research] Steering vectors research 🔬
#1472 opened May 16, 2023 by SlyEcho • Draft
62
Q4_0 scale selection using RMSE enhancement New feature or request Less than 4 bits Efforts related to viable quantized models using <4 bits research 🔬 Review Complexity : High Generally require indepth knowledge of LLMs or GPUs
#835 opened Apr 7, 2023 by sw • Draft
1
@sw
14
Study how LM Evaluation Harness works and try to implement it enhancement New feature or request generation quality Quality of model output help wanted Extra attention is needed high priority Very important issue research 🔬
#231 opened Mar 17, 2023 by ggerganov
9
ProTip! Exclude everything labeled bug with -label:bug.