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

340 Open 2,843 Closed
340 Open 2,843 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

Bug: CUDA error: out of memory - Phi-3 Mini 128k prompted with 20k+ tokens on 4GB GPU bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#7885 opened Jun 11, 2024 by kozuch
Bug: apparent pre-tokenization hash collision in get_vocab_base_pre() function in convert-hf-to-gguf.py script? Llama3 8B is mapped to smaug-bpe instead of llama-bpe bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7881 opened Jun 11, 2024 by jim-plus
Bug: get-wikitext-103.sh seems not working bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7878 opened Jun 11, 2024 by Eddie-Wang1120
2
Bug: GGML_ASSERT: ggml.c:12793: ne2 == ne02 zsh: abort ./finetune --model-base --train-data ./Llama3-8B-Chinese-Chat-fintune/111.tx bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7877 opened Jun 11, 2024 by CodeBobobo
Bug: multithreading for requests，model infer service failed bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7876 opened Jun 11, 2024 by liuzhipengchd
Feature Request: Add Paligemma support enhancement New feature or request
#7875 opened Jun 11, 2024 by nischalj10
4 tasks done
1
Bug: Random output after the last update bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7874 opened Jun 11, 2024 by alexcardo
1
Bug: I use llama-b3091-bin-win-llvm-arm64.zip Run qwen2-0_5b-instruct-q8_0.gguf and it cannot start. Is it a compilation error of llama-b3091-bin-win-llvm-arm64.zip? bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7873 opened Jun 11, 2024 by cxycxm
Bug: 'scripts/run-with-preset.py fails on --tensor-split` option when run on non-GPU-enabled system bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7864 opened Jun 10, 2024 by HanClinto
2
Bug: Possible precision loss when using KV cache bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7859 opened Jun 10, 2024 by uwu-420
Bug: server /completion endpoint no longer accepts numeric tokens bug Something isn't working medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7855 opened Jun 10, 2024 by matteoserva
1
@ggerganov
2
Refactor: Formalise Keys.General GGUF KV Store
#7836 opened Jun 8, 2024 by mofosyne
10
Bug: Server ends up in infinite loop if number of requests in the batch is greater than parallel slots with system prompt bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7834 opened Jun 8, 2024 by kdhingra307
2
Research: Im writing a paper on our medical finetuned llava-v1.6, research 🔬
#7831 opened Jun 8, 2024 by rohithbojja
2
iGPU offloading Bug: Memory access fault by GPU node-1 (appeared once only) AMD GPU Issues specific to AMD GPUs bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7829 opened Jun 8, 2024 by eliranwong
Converting finetune LLaVA model to gguf but while debugging getting result = self.mapping.get(key[:-len(suffix)]) as None
#7823 opened Jun 7, 2024 by INZA111
Bug: CUDA enabled docker container fails to launch bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#7822 opened Jun 7, 2024 by mblunt
1
Bug: Running a large model through the server using vulkan backend always generates gibberish after first call. bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#7819 opened Jun 7, 2024 by richardanaya
I am running two socket servers, and the CPU usage is at 50% bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7812 opened Jun 7, 2024 by superLiben
2
SIGSEGV on moderately complex grammar
#7810 opened Jun 7, 2024 by hoehrmann
@HanClinto
Bug: QWEN2 quantization GGML_ASSERT bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#7805 opened Jun 6, 2024 by bartowski1182
50
Bug: token generation seems to slow down for higher slots bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7802 opened Jun 6, 2024 by desperadoduck
3
Bug: JSON Schema-to-GBNF additionalProperties bugs (and other minor quirks) bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#7789 opened Jun 6, 2024 by HanClinto
1
Feature Request: Loading PeFT - LoRA adapters during runtime without prior merging enhancement New feature or request
#7788 opened Jun 6, 2024 by niranjanakella
4 tasks done
2
Refactor: investigate cleaner exception handling for server/server.cpp help wanted Extra attention is needed refactoring Refactoring
#7787 opened Jun 6, 2024 by mofosyne
3
ProTip! Mix and match filters to narrow down what you’re looking for.