Skip to content

Issues: cmp-nct/ggllm.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.

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

Clear current search query, filters, and sorts
28 Open 45 Closed
28 Open 45 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

#1 performance requirement
#83 opened Sep 27, 2023 by cmp-nct
Add support for AMX instructions (bf16 and/or int8)
#81 opened Aug 3, 2023 by WilliamTambellini
Metal support
#78 opened Aug 2, 2023 by ghost
2
Log the version of cuda that is being used
#77 opened Aug 1, 2023 by WilliamTambellini
linking error with static build
#76 opened Jul 31, 2023 by WilliamTambellini
4 tasks done
2
Performance - heads up enhancement New feature or request
#75 opened Jul 27, 2023 by cmp-nct
2
refactor gpt_params_parse, add validate_params function
#74 opened Jul 23, 2023 by maddes8cht Loading…
Would ggllm.cpp adopt the upcoming ggml fileformat (GGUF)?
#72 opened Jul 21, 2023 by klosax
1
--help , pipes and inconsistent help text finished
#71 opened Jul 19, 2023 by maddes8cht
7
Can't falcon_convert on OpenBuddy Falcon 7B model, KeyError [fixed] finished good first issue Good for newcomers
#68 opened Jul 18, 2023 by tak2hu
1
Even in interactive mode, multiturn conversation is not possible. bug Something isn't working finished
#67 opened Jul 17, 2023 by ehalit
3
Could we also get the Makefile updated to build a libfalcon.so
#64 opened Jul 14, 2023 by linuxmagic-mp
3
Upcoming PR - Pushing the Context limit to 8k+ for all existing Falcon models - Longrange Falcon flights enhancement New feature or request finished
#62 opened Jul 13, 2023 by cmp-nct
5
CMakeLists refinements for CUBLAS and phthread
#57 opened Jul 11, 2023 by luav Loading…
2
Performance at high context (18k+)
#56 opened Jul 11, 2023 by cmp-nct
4
Is there any GUI or Web UI for ggllm.cpp? enhancement New feature or request good first issue Good for newcomers
#52 opened Jul 9, 2023 by JohnClaw
13
Can you migrate the new server from llama.cpp to here?
#51 opened Jul 8, 2023 by maddes8cht
3
Does the prompt cache work? I got an alignment assert when I turned it on.
#42 opened Jul 5, 2023 by johnburkey
19
OpenBLAS and CLBlast support
#41 opened Jul 4, 2023 by Fr0d0Beutl1n
4
Steps forward - Tokenizer
#37 opened Jun 30, 2023 by cmp-nct
14
K Quant 64 support - quite a feat to integrate enhancement New feature or request
#34 opened Jun 28, 2023 by cmp-nct
4
Mul_mat Speedup??
#31 opened Jun 27, 2023 by boricuapab
12
Problem with cMake on Linux focal, Cuda
#22 opened Jun 23, 2023 by linuxmagic-mp
12
slow on 3090 and very high cpu usage
#17 opened Jun 20, 2023 by stupiding
6
Illegal instruction (core dumped) on Ubuntu 22.04.2
#11 opened Jun 19, 2023 by dRAT3
13
ProTip! What’s not been updated in a month: updated:<2024-06-18.