-
Notifications
You must be signed in to change notification settings - Fork 8.9k
Issues: ggerganov/llama.cpp
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
llama : support sliding window attention
performance
Speed related topics
#3377
opened Sep 28, 2023 by
ggerganov
Feature Request: Support for Meta Chameleon 7B and 34B
enhancement
New feature or request
#7995
opened Jun 18, 2024 by
arch-btw
4 tasks done
Support QuaRot quantization scheme
enhancement
New feature or request
#6444
opened Apr 2, 2024 by
EwoutH
Support for Sparse MoE models like Camelidae and Sparsetral
enhancement
New feature or request
good first issue
Good for newcomers
#5365
opened Feb 6, 2024 by
candre23
Support BitNet b1.58 ternary models
enhancement
New feature or request
Tensor Encoding Scheme
https://github.com/ggerganov/llama.cpp/wiki/Tensor-Encoding-Schemes
#5761
opened Feb 28, 2024 by
igorbarshteyn
support EAGLE models (new speculative model architecture faster than Medusa)
enhancement
New feature or request
#4391
opened Dec 9, 2023 by
BarfingLemurs
llama : combined beam search + grammar sampling strategy
generation quality
Quality of model output
good first issue
Good for newcomers
research 🔬
#2923
opened Aug 31, 2023 by
ggerganov
llama : tool for evaluating quantization results per layer
enhancement
New feature or request
generation quality
Quality of model output
#2783
opened Aug 25, 2023 by
ggerganov
Suport for Jamba JambaForCausalLM
enhancement
New feature or request
#6372
opened Mar 28, 2024 by
maziyarpanahi
4 tasks done
[Feature request] Any plans for AMD XDNA AI Engine support on Ryzen 7x40 processors?
#1499
opened May 17, 2023 by
KarmaMonk
3 of 4 tasks
Support CoreML like whisper.cpp?
help wanted
Extra attention is needed
macos
Issues specific to macOS
performance
Speed related topics
#1714
opened Jun 6, 2023 by
realcarlos
Eos and bos tokens can be redefined as additional tokens with other ids
enhancement
New feature or request
good first issue
Good for newcomers
#1776
opened Jun 9, 2023 by
vvasily
[IDEA] Global token enhancement/depression
help wanted
Extra attention is needed
research 🔬
#1865
opened Jun 15, 2023 by
elephantpanda
Using MPI w/ 65b model but each node uses the full RAM.
help wanted
Extra attention is needed
#2209
opened Jul 13, 2023 by
magnusviri
llama : add test for saving/loading sessions to the CI
good first issue
Good for newcomers
testing
Everything test related
#2631
opened Aug 16, 2023 by
ggerganov
Bug: Recent changes break Rocm compile on windows
bug-unconfirmed
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8612
opened Jul 21, 2024 by
sorasoras
CUDA non-determinism on identical requests
bug
Something isn't working
good first issue
Good for newcomers
#2838
opened Aug 27, 2023 by
phiharri
ci : fix Docker workflow
build
Compilation issues
help wanted
Extra attention is needed
#3628
opened Oct 15, 2023 by
ggerganov
Running Lllava in interactive mode just Quits after generating response without waiting for next prompt.
llava
LLaVa and multimodal
#3593
opened Oct 12, 2023 by
chigkim
Request: Nougat OCR Integration
help wanted
Extra attention is needed
model
Model specific
#3294
opened Sep 21, 2023 by
OhadRubin
ci : add Apple silicon (M1) macOS runners
good first issue
Good for newcomers
testing
Everything test related
#3469
opened Oct 4, 2023 by
ggerganov
Previous Next
ProTip!
Adding no:label will show everything without a label.