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 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

257 Open 3,815 Closed
257 Open 3,815 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

Misc. bug: -sm row does not work with --device bug Something isn't working
#10533 opened Nov 26, 2024 by mostlygeek
2
Compile bug: ARM neon instructions when compiling cuda bug-unconfirmed
#10531 opened Nov 26, 2024 by bruceloco
2
Misc. bug: Inconsistent Vulkan segfault bug-unconfirmed
#10528 opened Nov 26, 2024 by RobbyCBennett
Feature Request: enhancement New feature or request
#10520 opened Nov 26, 2024 by atozj
4 tasks done
Compile bug: [SYCL] Build fails from the latest master bug-unconfirmed
#10518 opened Nov 26, 2024 by qnixsynapse
2
[CANN] Compile bug: cann backend build failed when manually specify SOC_TYPE or gcc version that isn't verified Ascend NPU issues specific to Ascend NPUs
#10517 opened Nov 26, 2024 by leo-pony
@leo-pony
[CANN] Operator support Ascend NPU issues specific to Ascend NPUs enhancement New feature or request
#10512 opened Nov 26, 2024 by noemotiovon
4 tasks done
@hipudding
Misc. bug: SYCL builds >= 4040 have lower parallel performance by ~20% bug-unconfirmed
#10511 opened Nov 26, 2024 by 0xDEADFED5
Feature Request: Ability to cancel during prompt processing (llama_decode) enhancement New feature or request
#10509 opened Nov 26, 2024 by bdashore3
4 tasks done
1
Feature Request: Add "tokens per second" information in the Web UI enhancement New feature or request good first issue Good for newcomers server/webui
#10502 opened Nov 25, 2024 by ggerganov
4 tasks done
Compile bug: make CC='/opt/AMD/aocc-compiler-5.0.0/bin/clang' CXX='/opt/AMD/aocc-compiler-5.0.0/bin/clang++' AMD_ZEN4_BLIS_5=1 GGML_CUDA=1 GGML_CUDA_FORCE_CUBLAS=1 GML_CUDA_F16=1 GGML_CUDA_FORCE_MMQ=1 CUDA_USE_TENSOR_CORES=1 GGML_RPC=1 bug-unconfirmed
#10493 opened Nov 25, 2024 by KarlHeinzMali
1
Eval bug: Slow model loading w/ mmap bug-unconfirmed
#10478 opened Nov 25, 2024 by hg0428
Misc. bug: Serving of custom static files is broken when API key is set. bug-unconfirmed
#10475 opened Nov 24, 2024 by shibe2
Misc. bug: poor concurrent request performance with llama-server in macOS bug-unconfirmed
#10473 opened Nov 24, 2024 by pengjiang80
4
Feature Request: better cross entropy loss CUDA kernel enhancement New feature or request
#10467 opened Nov 23, 2024 by JohannesGaessler
4 tasks done
@JohannesGaessler
Misc. bug: Model provisioning doc link broken bug-unconfirmed
#10464 opened Nov 23, 2024 by paoletto
Compile bug: how to modify the cmakelists.txt bug-unconfirmed
#10462 opened Nov 23, 2024 by wangzd0209
Support for Macro-o1 by alibaba enhancement New feature or request
#10461 opened Nov 23, 2024 by Meshwa428
4 tasks done
4
ggml : add ANE backend help wanted Extra attention is needed research 🔬
#10453 opened Nov 22, 2024 by ggerganov
1
Bug: 【CANN】ggml-cann/aclnn_ops.cpp:3007: GGML_ASSERT(n_dims == src0->ne[0]) failed Ascend NPU issues specific to Ascend NPUs
#10451 opened Nov 22, 2024 by zyp2
7
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
9
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
23
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
1
12
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 have half the context limit of previous builds 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
4
ProTip! Exclude everything labeled bug with -label:bug.