-
Notifications
You must be signed in to change notification settings - Fork 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
How to evaluate my converted gguf model ? What all benchmark i can run and how to run on my converted model?
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8409
opened Jul 10, 2024 by
RakshitAralimatti
Bug: InternLM 2.5 Chat Tool Calls: Incorrect and Inconsistent Formatting
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8405
opened Jul 10, 2024 by
apresence
Bug: Renaming of executables breaks tutorials
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8397
opened Jul 9, 2024 by
gpacix
Bug: Model ignores system prompt when use Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
/completion
endpoint
bug-unconfirmed
medium severity
#8393
opened Jul 9, 2024 by
andreys42
Bug: [SYCL] Qwen2 MoE: 0 layers offloaded to GPU
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8387
opened Jul 9, 2024 by
ch1y0q
k cache quantization
enhancement
New feature or request
#8385
opened Jul 9, 2024 by
yancaoweidaode
4 tasks done
Bug: ggml/src/ggml.c: In function 'ggml_vec_mad_f16':
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8378
opened Jul 8, 2024 by
oldgithubman
Bug: Yi 1.5 segmentation fault
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8369
opened Jul 8, 2024 by
SimplyCorbett
Feature Request: support dynamic ntk rope scaling
enhancement
New feature or request
#8361
opened Jul 8, 2024 by
RunningLeon
4 tasks done
Steering sampling and decoding strategy with
num_beams
and do_sample
#8353
opened Jul 7, 2024 by
d-kleine
Feature Request: add indicator for which of MMQ vs cuBLAS is used
enhancement
New feature or request
#8350
opened Jul 7, 2024 by
isaac-mcfadyen
4 tasks done
Encounter the "newline in constant" error while compiling with MSVC
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8334
opened Jul 6, 2024 by
Yan-Xiangjun
Bug: Falcon 2 11B GGUF conversion works, but fails to read 8K context length from config.json
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8330
opened Jul 5, 2024 by
jim-plus
Huge performance degradation using latest branch on Intel Core Ultra 7 155H
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8328
opened Jul 5, 2024 by
aahouzi
Bug: make error
bug-unconfirmed
low severity
Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8313
opened Jul 5, 2024 by
lorihuang
Feature Request: Support for Meta: Multi Token Prediction Models
enhancement
New feature or request
#8297
opened Jul 4, 2024 by
sorasoras
4 tasks done
Bug: [SYCL] Inference not working correctly on multiple GPUs
bug-unconfirmed
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
#8294
opened Jul 4, 2024 by
ch1y0q
Feature Request: support for Gemini Nano?
enhancement
New feature or request
#8289
opened Jul 4, 2024 by
flatsiedatsie
4 tasks done
Add support for InternLM 2.5 1M context. Should be as good as command r+
enhancement
New feature or request
#8285
opened Jul 4, 2024 by
mirek190
4 tasks done
Why is the single input used incorrect, or no output?
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8276
opened Jul 3, 2024 by
QIANXUNZDL123
Feature Request: (server) Add option to always skip all queued tasks and to process the last one only (within one slot)
enhancement
New feature or request
#8275
opened Jul 3, 2024 by
stduhpf
4 tasks done
Bug: Llama 3 8b giving different outputs for same input (temperature 0)
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8274
opened Jul 3, 2024 by
LiquidGunay
Bug: Error when trying to use Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
./llama-gguf-split --merge
to merge split model gguf files back
bug-unconfirmed
medium severity
#8264
opened Jul 2, 2024 by
tybalex
Bug: Gemma2 Context switching forgets original input
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8251
opened Jul 2, 2024 by
Gomez12
Bug: CodeShell inference not working correctly
bug-unconfirmed
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8250
opened Jul 2, 2024 by
chiranko
ProTip!
Mix and match filters to narrow down what you’re looking for.