Skip to content

Issues: ggerganov/llama.cpp

examples : add configuration presets
#10932 opened Dec 21, 2024 by ggerganov
Open
changelog : libllama API
#9289 opened Sep 3, 2024 by ggerganov
Open 1
changelog : llama-server REST API
#9291 opened Sep 3, 2024 by ggerganov
Open 11
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

261 Open 3,935 Closed
261 Open 3,935 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

Compile bug: Linux ARM64 CPU build fails bug-unconfirmed
#10933 opened Dec 21, 2024 by SamuelTallet
examples : add configuration presets documentation Improvements or additions to documentation enhancement New feature or request examples good first issue Good for newcomers help wanted Extra attention is needed
#10932 opened Dec 21, 2024 by ggerganov
1 of 6 tasks
Misc. bug: All llama executables exit immediately without console output bug-unconfirmed
#10929 opened Dec 21, 2024 by Ikaron
OpenAI compatible response for /models has empty id and empty name bug-unconfirmed
#10924 opened Dec 20, 2024 by JeroenAdam
Compile bug: macOS Vulkan build fails bug Something isn't working build Compilation issues Vulkan Issues specific to the Vulkan backend
#10923 opened Dec 20, 2024 by soerenkampschroer
1
3
Compile bug: iOS version able to build not not able to run bug-unconfirmed
#10922 opened Dec 20, 2024 by Animaxx
1
Eval bug: gte-Qwen2 produces non-homogenous embedding vectors bug-unconfirmed
#10921 opened Dec 20, 2024 by bringfido-adams
Misc. bug: llama-server throws "Unsupported param: tools" bug-unconfirmed
#10920 opened Dec 20, 2024 by hsm207
Feature Request: (Server UI) Use remark for markdown rendering enhancement New feature or request good first issue Good for newcomers server/webui
#10915 opened Dec 20, 2024 by ngxson
4 tasks done
Extra newline and other tokens being produced in between paragraphs - llama-server bug-unconfirmed
#10914 opened Dec 20, 2024 by DocShotgun
Issues with LLaMA Binaries – Incomplete or Corrupted Downloads
#10908 opened Dec 20, 2024 by gitterbug131234
Feature Request: Multiple prompts for prompt caching enhancement New feature or request
#10904 opened Dec 19, 2024 by firelex
4 tasks done
No longer works on FreeBSD bug-unconfirmed
#10891 opened Dec 19, 2024 by ThisIsADogHello
Feature Request: SIMD on s390x using Vector Facility (-mzvector) enhancement New feature or request
#10888 opened Dec 18, 2024 by taronaeo
4 tasks done
Feature Request: support "encoding_format": "base64" in the */embeddings endpoints enhancement New feature or request good first issue Good for newcomers server/api server
#10887 opened Dec 18, 2024 by ggerganov
4 tasks done
Feature Request: Add support for SmolVLM enhancement New feature or request
#10877 opened Dec 17, 2024 by iacore
4 tasks done
Misc. bug: [SERVER] Multiple slots, generation speed is degraded after each generation/slot used bug-unconfirmed
#10860 opened Dec 17, 2024 by ExtReMLapin
10
Misc. bug: llama-bench SEGFAULTS w/ SYCL/HIP backend, however llama-cli seems to work bug-unconfirmed
#10850 opened Dec 16, 2024 by lhl
6
Compile bug: Compiling on Maxwell architecture 52 cuda12.7 bug-unconfirmed
#10849 opened Dec 16, 2024 by envolution
Feature Request: Q6_0 quant enhancement New feature or request
#10848 opened Dec 16, 2024 by Nexesenex
4 tasks done
Eval bug: ggml_metal_encode_node: error: unsupported op 'IM2COL' bug-unconfirmed
#10845 opened Dec 16, 2024 by beginor
1
Eval bug: Qwen2-VL Hallucinates image content on Vulkan backend bug-unconfirmed
#10843 opened Dec 15, 2024 by stduhpf
12
Feature Request: Add support for the WePOINTS/POINTS1.5 model enhancement New feature or request
#10834 opened Dec 15, 2024 by rcbevans
4 tasks done
Misc. bug: llama 3.2 3B : for Q4 quantized models repeated output is generating without hitting [end of text] bug-unconfirmed
#10824 opened Dec 14, 2024 by Ramees025
4
Is LayerSkip / self-speculative decoding possible (requires getting one intermediate layer's output + some KV cache changes)?
#10820 opened Dec 13, 2024 by tc-wolf
1
ProTip! Add no:assignee to see everything that’s not assigned.