Skip to content

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.

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

314 Open 3,253 Closed
314 Open 3,253 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Llama-Quantize : Layers quantized in the wrong order, thus damaging the variable bits tensor quants scheme consistency. bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#9005 opened Aug 12, 2024 by Nexesenex
cannot import name 'BaseVocab' from 'gguf' bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8996 opened Aug 12, 2024 by garyyang85
1
Bug: Phi-3 mini 128k performance degradation with kv size > 8k (server) bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8995 opened Aug 12, 2024 by steampunque
3
Feature Request: Add support for EXAONE-3.0-7.8B-Instruct model enhancement New feature or request
#8991 opened Aug 12, 2024 by chris-jaehoon
4 tasks done
1
Bug: GGML_ASSERT(llama_add_eos_token(model) != 1) failed llama-server critical error with flan-t5 models bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8990 opened Aug 12, 2024 by fabiomatricardi
1
3
Bug: Long sample times with --top-k 0 bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8988 opened Aug 11, 2024 by Azirine
2
Feature Request: MiniCPM 2.6 model support? enhancement New feature or request
#8977 opened Aug 10, 2024 by ttamoud
4 tasks done
2
Bug: llama-cli out "error: input is empty" and end bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8976 opened Aug 10, 2024 by yanite
1
Bug: llama-server with --system-prompt-file stops abruptly without any error bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8975 opened Aug 10, 2024 by pritam-dey3
1
2
Bug: llama-export-lora fails merging a T5 model with its LoRA adapter bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8974 opened Aug 10, 2024 by cyanic-selkie
1
4
Bug: uncached prompt is not used for penalty bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8971 opened Aug 10, 2024 by z80maniac
Bug: Adreno740 GPU device can't load model in Android system bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#8965 opened Aug 10, 2024 by FranzKafkaYu
Feature Request: Support AWS inferentia inf2 instances enhancement New feature or request
#8954 opened Aug 9, 2024 by virajkanwade
4 tasks done
1
Feature Request: [GRAMMAR] Easier way to negate string ((^) with sequence) enhancement New feature or request
#8953 opened Aug 9, 2024 by ExtReMLapin
4 tasks done
5
Bug: BigLlama-3.1-681B-Instruct requires llama_model_max_nodes to return a higher value bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8950 opened Aug 9, 2024 by nicoboss
1
2
Bug: Speed regression from early this year bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8945 opened Aug 9, 2024 by IndustrialOne
7
Feature Request: add support to LLaVA OneVision enhancement New feature or request
#8944 opened Aug 9, 2024 by alexrah
4 tasks done
Feature Request: echo=true in llama-server enhancement New feature or request
#8942 opened Aug 9, 2024 by ciaran-regan-ie
4 tasks done
1
Bug: BF16 is very slow bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8941 opened Aug 9, 2024 by calvintwr
3
Feature Request: Ovis1.5-Gemma2-9B model support? enhancement New feature or request
#8940 opened Aug 9, 2024 by liuzl
4 tasks done
1
Bug: When --parallel 4 is turned ON, the inferring result is apparently like fool .But when --parallel 4 is turned OFF everything is OK ? bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8935 opened Aug 8, 2024 by hzgdeerHo
4
Feature Request: Support vulkan when building on Android enhancement New feature or request
#8933 opened Aug 8, 2024 by XinyuGroceryStore
4 tasks done
Bug: Kompute exits before loading model when offloading to GPU bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#8932 opened Aug 8, 2024 by mi4code
1
Bug: exception while rasing a another exception in convert_llama_ggml_to_gguf script bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#8929 opened Aug 8, 2024 by farbodbj
Bug: Latest version of convert_hf_to_gguf not compatible with gguf 0.9.1 from pip bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#8925 opened Aug 8, 2024 by Ru13en
ProTip! What’s not been updated in a month: updated:<2024-07-12.