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

697 Open 1,064 Closed
697 Open 1,064 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

finetune: terminate called after throwing an instance of 'std::bad_alloc' bug-unconfirmed
#4389 opened Dec 9, 2023 by mailgpa
4 tasks done
Enhancement: We need CogVLM support - extremely good image and text analysis, feels like a multi generational step forward.
#4387 opened Dec 9, 2023 by cmp-nct
Add QuIP Sharp Support - New Quantization method with amazing 2-bit performance ( close to 16 bit ) enhancement New feature or request
#4386 opened Dec 9, 2023 by errorsandwarnings
5
Recoverable Error Handling enhancement New feature or request
#4385 opened Dec 9, 2023 by martindevans
4 tasks done
[Question] GPU vs Metal performance & Seeding models
#4384 opened Dec 9, 2023 by aramcheck
Mixtral MOE enhancement New feature or request
#4381 opened Dec 8, 2023 by fakerybakery
13
llava: batch inference
#4378 opened Dec 8, 2023 by Borobo
1
High inference time
#4377 opened Dec 8, 2023 by adeelhasan19
Process crash due to white spaces in grammar file. bug-unconfirmed
#4376 opened Dec 8, 2023 by darxkies
4 tasks done
3
How to use batching
#4372 opened Dec 8, 2023 by EricLBuehler
Server example sampling is partially broken bug-unconfirmed
#4370 opened Dec 8, 2023 by kalomaze
Running convert fails with BadZipFile (Bad CRC-32) bug-unconfirmed
#4365 opened Dec 7, 2023 by itsJoKr
4 tasks done
Implementing TokenMonster tokenizer enhancement New feature or request
#4363 opened Dec 7, 2023 by Sovenok-Hacker
3
Compilation error on Mac M2 bug-unconfirmed
#4361 opened Dec 7, 2023 by leocus
4 tasks done
2
Errors w/ BPE tokenizers (GGML_ASSERT: llama.cpp:2029: codepoints_from_utf8(word).size() > 0 and more) bug-unconfirmed
#4360 opened Dec 7, 2023 by lhl
4 tasks done
1
llama : benchmark for Apple Silicon A-series mobile chips performance Speed related topics
#4358 opened Dec 7, 2023 by ggerganov
Possible of implementing mamba ssm enhancement New feature or request help wanted Extra attention is needed
#4353 opened Dec 7, 2023 by tikikun
4 tasks done
llama.cpp inference too long bug-unconfirmed
#4352 opened Dec 7, 2023 by wzg-zhuo
1
Compilation Error bug-unconfirmed
#4346 opened Dec 6, 2023 by mitesh741
When I try to do finetuning I get a GGML_ASSERT: ggml.c:16911: np < GGML_MAX_PARAMS error. bug-unconfirmed
#4342 opened Dec 6, 2023 by Taikono-Himazin
4 tasks done
9
Separation of declarations in llama.cpp enhancement New feature or request
#4339 opened Dec 5, 2023 by jmikedupont2
llm_build_context::build_<X>() functions refactor enhancement New feature or request
#4338 opened Dec 5, 2023 by jmikedupont2
[Feature request] Support for "XVERSE" model enhancement New feature or request
#4337 opened Dec 5, 2023 by aspwow
Add GPU support for training enhancement New feature or request
#4336 opened Dec 5, 2023 by gocursor
2
Grammar based decoding doesn't work with DeepSeek models bug-unconfirmed
#4333 opened Dec 5, 2023 by Ghatage
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.