-
Notifications
You must be signed in to change notification settings - Fork 9.3k
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
ERROR: Can't Compile llama.cpp on Mac OS Sequoia (September 2024 update)
bug-unconfirmed
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9575
opened Sep 21, 2024 by
joseph777111
Bug: ROCM 7900xtx output random garbage with qwen1.5/14B after recent update
bug-unconfirmed
critical severity
Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#9568
opened Sep 20, 2024 by
sorasoras
Bug: gguf pypi package corrupts environment
bug-unconfirmed
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9566
opened Sep 20, 2024 by
vladmandic
Bug: Release version less accurate than Debug version consistently
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9564
opened Sep 20, 2024 by
SwamiKannan
Bug: Model isn't loading
bug-unconfirmed
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9563
opened Sep 20, 2024 by
iladshyan
[CANN]Bug: Can't compile ggml/src/CMakeFiles/ggml.dir/ggml-cann/acl_tensor.cpp.o
bug-unconfirmed
critical severity
Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#9560
opened Sep 20, 2024 by
pangbobi
Bug: llama cpp server arg LLAMA_ARG_N_GPU_LAYERS doesn't follow the same convention as llama cpp python n_gpu_layers
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9556
opened Sep 20, 2024 by
mvonpohle
Bug: Unreadable output from android example project
bug-unconfirmed
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#9555
opened Sep 20, 2024 by
xunuohope1107
Feature Request: Support GRIN-MoE by Microsoft
enhancement
New feature or request
#9552
opened Sep 19, 2024 by
GlasslessPizza
4 tasks done
Bug: KV quantization fails when using vulkan
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9551
opened Sep 19, 2024 by
jmars
Bug: Build fails on i386 systems
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
Vulkan
Issues specific to the Vulkan backend
#9545
opened Sep 19, 2024 by
yurivict
Bug: Lower performance in pre-built binary llama-server, Since llama-b3681-bin-win-cuda-cu12.2.0-x64
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9530
opened Sep 18, 2024 by
tobchef
Bug: duplicate vulkan devices being detected on windows
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9516
opened Sep 17, 2024 by
tempstudio
metal : increase GPU duty-cycle during inference
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
help wanted
Extra attention is needed
performance
Speed related topics
#9507
opened Sep 16, 2024 by
ggerganov
Bug: Lower performance in SYCL vs IPEX LLM.
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9505
opened Sep 16, 2024 by
adi-lb-phoenix
Bug: llama-bench: split-mode flag doesn't recognize argument 'none'
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9501
opened Sep 16, 2024 by
letter-v
Feature Request: RDMA support for rpc back ends
enhancement
New feature or request
#9493
opened Sep 15, 2024 by
slavonnet
4 tasks done
Bug: llama-server api first query very slow
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9492
opened Sep 15, 2024 by
bosmart
Bug: andriod compiling bug, with vulkan open
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9489
opened Sep 15, 2024 by
bitxsw93
[CANN]Feature Request: Support OrangeAIPRO 310b CANN
Ascend NPU
issues specific to Ascend NPUs
enhancement
New feature or request
#9481
opened Sep 14, 2024 by
StudyingLover
4 tasks done
Bug: There is an issue to execute llama-baby-llama.
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9478
opened Sep 14, 2024 by
Foreverythin
Bug: logit_bias Persists Across Requests When cache_prompt Is Enabled in llama.cpp Server
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9477
opened Sep 14, 2024 by
jeanromainroy
Bug: [SYCL] Error loading models larger than Q4
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9472
opened Sep 13, 2024 by
HumerousGorgon
Bug: Random inputs generated automatically in llama-cli
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#9456
opened Sep 12, 2024 by
Abhranta
Previous Next
ProTip!
Follow long discussions with comments:>50.