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
Specific suggested wiki "Feature Matrix" updates pertaining to SYCL.
enhancement
New feature or request
#7415
opened May 20, 2024 by
ghchris2021
ci failing on main branch
bug-unconfirmed
high priority
Very important issue
#7403
opened May 20, 2024 by
mofosyne
FA2 - P40 || Mixtral partial GPU offload Gibberish
bug-unconfirmed
#7400
opened May 19, 2024 by
askmyteapot
speedup ROCm AMD Unified Memory Architecture
enhancement
New feature or request
#7399
opened May 19, 2024 by
Djip007
Llama.cpp server doesn't return grammar error messages when in streaming mode
bug-unconfirmed
#7391
opened May 19, 2024 by
richardanaya
Possible bug in the 'deepseek-coder' chat template's system message
bug-unconfirmed
#7385
opened May 19, 2024 by
jukofyork
Different result between use llama_tokenize and python original transformers tokenizer
#7384
opened May 19, 2024 by
Liufeiran123
Can I handle multiple images in the same context?
bug-unconfirmed
#7364
opened May 18, 2024 by
Eriter555
[SYCL] include shared libs in sycl release
enhancement
New feature or request
#7361
opened May 18, 2024 by
gfody
[Android/Termux] Significantly higher RAM usage with Vulkan compared to CPU only
bug-unconfirmed
#7351
opened May 17, 2024 by
egeoz
AMD ROCm: 8x22B Model Causes 100% GPU Utilization Stall
bug-unconfirmed
#7344
opened May 17, 2024 by
Trat8547
convert.py still fails on llama3 8B-Instruct downloaded directly from Meta (Huggingface works)
bug-unconfirmed
#7339
opened May 17, 2024 by
aleloi
Segmentation Fault on GPU
training
Fine-tuning and training stuff
#7337
opened May 17, 2024 by
djain-fujitsu
llava surgery script for new llava-arch model from Intel
bug-unconfirmed
#7333
opened May 16, 2024 by
KohakuBlueleaf
Add support for multilingual Viking models, please.
enhancement
New feature or request
#7309
opened May 15, 2024 by
JohnClaw
Possible performance boost with 2-pass online softmax
bug-unconfirmed
#7306
opened May 15, 2024 by
zixuanweeei
Previous Next
ProTip!
Adding no:label will show everything without a label.