Skip to content

Issues: abetlen/llama-cpp-python

Roadmap for v0.2
#487 opened Jul 18, 2023 by abetlen
Open 1
Add batched inference
#771 opened Sep 30, 2023 by abetlen
Open 37
Improve installation process
#1178 opened Feb 12, 2024 by abetlen
Open 8
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
69 Open 100 Closed
69 Open 100 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Feature request: ability to tokenize a list of strings _or_ keep the tokenizer warm enhancement New feature or request
#1763 opened Sep 25, 2024 by lsorber
Add support T5 (encode-decoder) models at API level and server enhancement New feature or request
#1681 opened Aug 14, 2024 by fabiomatricardi
Feat: Add support for Llama 3.1 function calling enhancement New feature or request
#1618 opened Jul 24, 2024 by qnixsynapse
3
Add support for croos-encoders enhancement New feature or request
#1611 opened Jul 20, 2024 by perpendicularai
3
Pull from Ollama repo functionality enhancement New feature or request
#1607 opened Jul 18, 2024 by ericcurtin
4
How to log raw token generation? enhancement New feature or request
#1546 opened Jun 21, 2024 by sisi399
Multi-arch support for pre-built cpu wheel enhancement New feature or request
#1506 opened Jun 5, 2024 by abetlen
Improve pre-built wheel CI times by only building llama.cpp once per platform enhancement New feature or request
#1505 opened Jun 5, 2024 by abetlen
1
Include usage key in create_completion when streaming enhancement New feature or request
#1498 opened May 30, 2024 by zhudotexe
1
2
Please add response_format to create_completion enhancement New feature or request
#1478 opened May 23, 2024 by dtkettler
Add support for auto setting n_gpu_layers from gguf and available vram size enhancement New feature or request
#1456 opened May 14, 2024 by abetlen
arm64 builds for CUDA enhancement New feature or request
#1446 opened May 10, 2024 by mcvella
1
Add Nous Hermes 2 Pro function calling ChatHandler. enhancement New feature or request
#1429 opened May 5, 2024 by stygmate
1
Is loading of control vectors supported? enhancement New feature or request
#1363 opened Apr 19, 2024 by edwinRNDR
1
[REQUEST] Accept raw token IDs in stop parameter enhancement New feature or request
#1360 opened Apr 18, 2024 by ddh0
11
Hermes 2 Pro Full Chat Format Support enhancement New feature or request
#1339 opened Apr 9, 2024 by abetlen
Allow any format for X-Request-Id enhancement New feature or request
#1337 opened Apr 9, 2024 by ging-dev
4 tasks done
1
Models with multiple chat templates enhancement New feature or request
#1336 opened Apr 8, 2024 by CISC
7
Add command-r support like llamacpp has enhancement New feature or request
#1279 opened Mar 16, 2024 by rombodawg
5
Does this lib support contrastive search decoding ? enhancement New feature or request
#1253 opened Mar 5, 2024 by congson1293
2
Add Self-Extend support? enhancement New feature or request
#1242 opened Mar 1, 2024 by theaerotoad
6
llama_cpp.server save chat log enhancement New feature or request
#1224 opened Feb 26, 2024 by riverzhou
[Implement Optimization] Skip Inference for Predefined Tokens in Response Formatting enhancement New feature or request
#1203 opened Feb 21, 2024 by Garstig
3
Improve installation process enhancement New feature or request help wanted Extra attention is needed
#1178 opened Feb 12, 2024 by abetlen
8
Have you thought about adding quantum cache or 8 bit cache? enhancement New feature or request
#1161 opened Feb 5, 2024 by Ph0rk0z
2
ProTip! What’s not been updated in a month: updated:<2025-04-25.