Skip to content

Issues: ollama/ollama

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

Clear current search query, filters, and sorts
464 Open 2,051 Closed
464 Open 2,051 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

Ollama: torch.OutOfMemoryError: CUDA out of memory bug Something isn't working
#8616 opened Jan 27, 2025 by kennethwork101
Problems with deepseek-r1:671b, ollama keeps crashing on long answers bug Something isn't working
#8614 opened Jan 27, 2025 by fabiounixpi
7
[v0.5.4] Download timeouts cause download cache corruption. Any download that needs to be retried by re-running ollama ends up corrupted at 100% download(file sha256-sha256hash-partial-0 not found). bug Something isn't working
#8613 opened Jan 27, 2025 by esperanza-esperanza
2
/clear not actually clearing bug Something isn't working
#8611 opened Jan 27, 2025 by iplayfast
1
Error fetching ANY model locally bug Something isn't working
#8605 opened Jan 27, 2025 by devroopsaha744
4
Deepseek-R1 671B - Segmentation Fault Bug bug Something isn't working
#8602 opened Jan 27, 2025 by Notbici
2
Error: an error was encountered while running the model: unexpected EOF (8x H100, deepseek-r1:671b) bug Something isn't working
#8599 opened Jan 27, 2025 by jwatte
1
Error Running Mistral Nemo Imported from .safetensors bug Something isn't working
#8598 opened Jan 26, 2025 by aallgeier
Error: llama runner process has terminated: error loading model: unable to allocate CUDA0 buffer (4x L40S, 384GB system RAM, Deepseek-R1) bug Something isn't working
#8597 opened Jan 26, 2025 by orlyandico
12
Ollama on WSL2 detects GPU but timesout when running inference bug Something isn't working
#8596 opened Jan 26, 2025 by rz1027
4
High idle power consumption due to persistent CUDA initialization bug Something isn't working
#8591 opened Jan 26, 2025 by SvenMeyer
4
Compile ollama failed in debian bug Something isn't working
#8589 opened Jan 26, 2025 by johndoanee
Error: "not authorized to push" bug Something isn't working
#8584 opened Jan 25, 2025 by NLP-man
1
Deepseek R1 throwing weird generation DDDDDDDDDDDDDDDDDDDDDDDDDDDDDDD bug Something isn't working
#8583 opened Jan 25, 2025 by amrrs
5
ollama version is 0.5.7-0-ga420a45-dirty bug Something isn't working
#8582 opened Jan 25, 2025 by Mario4272
FHS Violation bug Something isn't working
#8580 opened Jan 25, 2025 by rgammans
Ollama cannot start because it try to create an existing directory bug Something isn't working
#8572 opened Jan 25, 2025 by brianhuster
1
running deepseek r1 671b on 64GB / 128GB ram mac gives Error: llama runner process has terminated: signal: killed bug Something isn't working
#8571 opened Jan 25, 2025 by duttaoindril
8
can not run this on intel Xe gpu bug Something isn't working
#8570 opened Jan 24, 2025 by 1009058470
2
Model loaded each time bug Something isn't working
#8566 opened Jan 24, 2025 by PrinceSajjadHussain
4
Error when trying to download deepseek-r1:7b bug Something isn't working
#8565 opened Jan 24, 2025 by makhlwf
9
Error: server metal not listed in available servers map bug Something isn't working
#8564 opened Jan 24, 2025 by felix021
2
When LLM generates empty string response, eval_duration is missing. bug Something isn't working
#8553 opened Jan 23, 2025 by wch
error: unsupported op 'CPY' bug Something isn't working
#8549 opened Jan 23, 2025 by devlux76
1
deepseek-r1 qwen variants use a new pre-tokenizer, which is not implemented in the llama.cpp version used bug Something isn't working
#8547 opened Jan 23, 2025 by sealad886
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.