Skip to content

Issues: LostRuins/koboldcpp

Beta
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

341 Open 668 Closed
341 Open 668 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

Feature Request: Default Generation Parameters for API Endpoints enhancement New feature or request
#1525 opened May 5, 2025 by hronoas
2
Qwen3-30B-A3B thinks endlessly
#1522 opened May 3, 2025 by csavages
5
incompatible with that of previous function "cospi"
#1521 opened May 3, 2025 by zz64
1
Qwen3-30B-A3B gibberish
#1520 opened May 3, 2025 by EugeoSynthesisThirtyTwo
18
GUI model selection popup doesnt work anymore bug Something isn't working changes needed help wanted Extra attention is needed high priority needs review needs review
#1514 opened Apr 30, 2025 by stubkan
8
Any way to circumvent the virtual limit on --defaultgenamount?
#1513 opened Apr 30, 2025 by jhemmond
8
Help GUI failed to start
#1511 opened Apr 29, 2025 by xglexe
6
Possible to use Reranking model?
#1508 opened Apr 28, 2025 by mercurial-moon
1
Can't get plamo-13b to run under any circumstances. Is it not supported?
#1506 opened Apr 27, 2025 by Alexamenus
28
TextDB via API
#1504 opened Apr 26, 2025 by mercurial-moon
9
Feature Request: Orpheus-TTS
#1500 opened Apr 24, 2025 by h3ndrik
1
Option to hide <think> tag while generating
#1499 opened Apr 24, 2025 by Shura-Joy
2
CUDA error: function failed to launch on multi GPU in ggml-cuda during matrix multiplication
#1497 opened Apr 21, 2025 by riunxaio
4
Launch problem on AMD Vega 64
#1493 opened Apr 19, 2025 by pin24
2
Request to merge Microsoft/BitNet functionality, as it is fast, up-to-date, and necessary
#1491 opened Apr 19, 2025 by windkwbs
models path
#1490 opened Apr 18, 2025 by tehMArs
1
Make a separate class for outputs inside the pipeline
#1488 opened Apr 17, 2025 by kaihatsu-dg
8
Question/Request
#1487 opened Apr 17, 2025 by Reithan
3
--cli mode causes koboldcpp to close instantly or experience an error once input is sent.
#1482 opened Apr 14, 2025 by wildwolf256
7
GGML_ASSERT(cgraph->n_nodes < cgraph->size) failed - New Version
#1481 opened Apr 14, 2025 by DerRehberg
4
[Feature Request] optimize use of VRAM memory (layers offloading calculation + KV context quantization size calculation)
#1480 opened Apr 13, 2025 by parsedone
8
Just a harmless warning in the Windows build
#1479 opened Apr 12, 2025 by jojorne
2
Suggestion: Different Images for each chat participant
#1476 opened Apr 10, 2025 by pbz134
1
Gemma 3 + mmproj + flashattention falls back to CPU decoding when using --quantkv
#1473 opened Apr 8, 2025 by vlawhern
5
"async" CUDA<n> uploads appear to be non-concurrent
#1472 opened Apr 8, 2025 by lee-b
1
ProTip! Add no:assignee to see everything that’s not assigned.