-
Notifications
You must be signed in to change notification settings - Fork 10.8k
Issues: ggml-org/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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Eval bug: GGML_ASSERT(hparams.n_embd_head_k % ggml_blck_size(type_k) == 0) failed
bug-unconfirmed
#12033
opened Feb 22, 2025 by
AbdullahMPrograms
Misc. bug: Web-UI now unusably slow due to animations
bug-unconfirmed
#12026
opened Feb 22, 2025 by
clort81
Eval bug: unknown pre-tokenizer type: 'deepseek-r1-qwen'
bug-unconfirmed
#12021
opened Feb 22, 2025 by
wr131
Misc. bug: Concurrency Limitation: Only 6 Inferences Run Simultaneously When Setting
--parallel
> 6
bug-unconfirmed
#12013
opened Feb 21, 2025 by
karanotsingyu
[CANN] Compile bug: no matching function for call to 'CastIntrinsicsImpl' Ascend NPU issues specific to Ascend NPUs
#12010
opened Feb 21, 2025 by
Cikaros
Eval bug: does llama.cpp support Intel AMX instruction? how to enable it
bug-unconfirmed
#12003
opened Feb 21, 2025 by
montagetao
Misc. bug: add tool_calls id in response in server
bug-unconfirmed
#11992
opened Feb 21, 2025 by
henryclw
Feature Request: add Kernel level verbose option
enhancement
New feature or request
#11985
opened Feb 20, 2025 by
0400H
4 tasks done
Misc. bug: llama-cli '--log-disable' parameter omits response
bug-unconfirmed
#11983
opened Feb 20, 2025 by
nmandic78
Eval bug: CANNOT LINK EXECUTABLE "./llama-cli": library "libomp.so" not found: needed by main executable
bug-unconfirmed
#11979
opened Feb 20, 2025 by
Krallbe68
GGML to GGUF FAIL Quantized tensor bytes per row (5120) is not a multiple of Q2_K type size (84)
#11976
opened Feb 20, 2025 by
chokoon123
tensor 'blk.25.ffn_down.weight' has invalid ggml type 42 (NONE)
bug-unconfirmed
#11975
opened Feb 20, 2025 by
evaninf
Misc. bug: Sporadic MUL_MAT Failures in test-backend-ops for Nvidia backend
bug-unconfirmed
#11972
opened Feb 20, 2025 by
ShanoToni
Misc. bug: The KV cache is sometimes truncated incorrectly when making v1/chat/completions API calls
bug
Something isn't working
#11970
opened Feb 20, 2025 by
vnicolici
Eval bug: Ram boom after using llama-bench with cuda12.8 and deepseekr1q6
bug-unconfirmed
#11965
opened Feb 20, 2025 by
Xxianna
Misc. bug: Rpc-server does not use opencl backend on Android.
bug-unconfirmed
#11957
opened Feb 19, 2025 by
belog2867
Misc. bug: Segmentation fault when importing model to opencl buffer
bug-unconfirmed
#11953
opened Feb 19, 2025 by
zhouzengming
Previous Next
ProTip!
Updated in the last three days: updated:>2025-02-20.