Skip to content

Issues: ggerganov/llama.cpp

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 7
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

258 Open 3,790 Closed
258 Open 3,790 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

ggml : add ANE backend help wanted Extra attention is needed research 🔬
#10453 opened Nov 22, 2024 by ggerganov
Bug: 【CANN】ggml-cann/aclnn_ops.cpp:3007: GGML_ASSERT(n_dims == src0->ne[0]) failed bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#10451 opened Nov 22, 2024 by zyp2
3
Bug: Heavy throttling during token generation on Apple Silicon bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#10444 opened Nov 21, 2024 by Azirine
4
Bug: Flash Attention performs worse under ROCM bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#10439 opened Nov 20, 2024 by Mushoz
15
Bug: Severe Performance Degradation on Q4_0 CPU-only with MacOS / Apple Silicon M2, after PR#9921 / Version 4081 bug Something isn't working
#10435 opened Nov 20, 2024 by AndreasKunar
7
Why server slot's cache_prompt is false by default? bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#10427 opened Nov 20, 2024 by Nekotekina
Bug: SYCL builds >= b4069 fail to allocate SYCL0 buffer bug-unconfirmed critical severity Used to report critical severity bugs in llama.cpp (e.g. Crashing, Corrupted, Dataloss)
#10421 opened Nov 20, 2024 by 0xDEADFED5
3
Bug: Vulkan vk::DeviceLostError with multithreaded environment bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#10420 opened Nov 20, 2024 by ddwkim
2
Bug: Build failure in master on Arch Linux with CUDA enabled bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#10414 opened Nov 19, 2024 by momokrono
Bug: run llama.cpp failed with Vulkan-supported and quantized model in Android Termux bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#10406 opened Nov 19, 2024 by linxhome
4
Research: bench of the llamacpp research 🔬
#10405 opened Nov 19, 2024 by jumbo-q
1 of 5 tasks
Feature Request: Code Explanation Tutoria enhancement New feature or request
#10399 opened Nov 19, 2024 by Tangzhongyi834
4 tasks done
1
Bug: Server hangs when number of threads used for decoding > number of CPUs it runs on bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#10397 opened Nov 19, 2024 by KevinRSX
Feature Request: [CANN] Use the RoPE operator provided by aclnn enhancement New feature or request
#10396 opened Nov 19, 2024 by noemotiovon
4 tasks done
Qwen 32B: server breaks stream abruptly when above 9K context bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#10393 opened Nov 18, 2024 by JeroenAdam
8
Research: Design of llama-bench research 🔬
#10386 opened Nov 18, 2024 by jumbo-q
1 of 5 tasks
2
Refactor: Allow adding both tokens and embeddings to llama_batch
#10381 opened Nov 18, 2024 by ngxson
1
Bug: flash-attn can't use bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#10378 opened Nov 18, 2024 by Tangzhongyi834
2
Feature Request: Apply LoRA adapters per-request enhancement New feature or request
#10377 opened Nov 18, 2024 by ngxson
4 tasks done
1
LORA Adapter Hot Swap Implementation Problem
#10374 opened Nov 18, 2024 by michaellin99999
4
Bug: No docs explain the value for cache-type-k/v bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#10373 opened Nov 18, 2024 by phazei
Bug: Objective-C++ Compilation Issues when running swift build or swift test with Swift Package Manager bug-unconfirmed high severity Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
#10371 opened Nov 18, 2024 by will-lumley
Bug: convert_hf_to_gguf bluescreens windows with very large models bug-unconfirmed low severity Used to report low severity bugs in llama.cpp (e.g. cosmetic issues, non critical UI glitches)
#10365 opened Nov 17, 2024 by candre23
ggml : reintegrate the AMX backend into the CPU backend refactoring Refactoring
#10359 opened Nov 17, 2024 by ggerganov
Bug: rope-scale and rope-scaling parameters not being parsed in llama.cpp server bug-unconfirmed medium severity Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
#10355 opened Nov 17, 2024 by henryclw
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.