Skip to content

Pull requests: ggerganov/llama.cpp

New pull request New
230 Open 3,254 Closed
230 Open 3,254 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[no ci] Add Nix and Flox install instructions Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7899 opened Jun 12, 2024 by bryanhonof Loading…
2 of 4 tasks
Implement non-mapped async IO for CUDA on Windows. Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7896 opened Jun 12, 2024 by mtavenrath Loading…
2 of 4 tasks
9
convert-hf-to-gguf-update.py: Added Ukrainian tokens into string python python script changes Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7888 opened Jun 11, 2024 by AragonerUA Loading…
2 of 4 tasks
Implemented Spellcheck for Llama.cpp examples Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7884 opened Jun 11, 2024 by Ferruolo Loading…
2 of 4 tasks
json: better support for "type" unions (e.g. nullable arrays w/ typed items) examples python python script changes Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix server testing Everything test related
#7863 opened Jun 10, 2024 by ochafik Loading…
2
[SYCL] Revert "use the correct SYCL context for host USM allocations" Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#7858 opened Jun 10, 2024 by AidanBeltonS Loading…
5
gguf-dump.py: add --markdown dump output python python script changes Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7853 opened Jun 10, 2024 by mofosyne Loading…
1
Type cast AVX512_BF16 data types based on compiler instead of the OS platform ggml changes relating to the ggml tensor library for machine learning Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7851 opened Jun 10, 2024 by Srihari-mcw Loading…
AVX IQ Quants ggml changes relating to the ggml tensor library for machine learning Review Complexity : High Generally require indepth knowledge of LLMs or GPUs
#7845 opened Jun 10, 2024 by netrunnereve • Draft
examples: refine tensor dump examples Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level
#7844 opened Jun 10, 2024 by zhouwg Loading…
Fix conversion of unnormalized BF16->BF16 weights python python script changes Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7843 opened Jun 10, 2024 by CISC Loading…
[WIP] json: fix additionalProperties, allow space after enum/const examples python python script changes Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level server testing Everything test related
#7840 opened Jun 9, 2024 by ochafik • Draft
1 of 2 tasks
4
update: support Qwen2-57B-A14B python python script changes Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level
#7835 opened Jun 8, 2024 by legraphista Loading…
25
Avoid division-by-zero on 0-weights ggml changes relating to the ggml tensor library for machine learning Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7825 opened Jun 7, 2024 by CISC Loading…
5
Add Qwen2MoE 57B-A14B Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7814 opened Jun 7, 2024 by CISC Loading…
1
build: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... breaking change Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility. devops improvements to build systems and github actions documentation Improvements or additions to documentation examples help wanted Extra attention is needed merge ready indicates that this may be ready to merge soon and is just holding out in case of objections nix Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment python python script changes Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level script Script related server SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#7809 opened Jun 6, 2024 by ochafik Loading…
36
[WIP] json: support integer minimum, maximum, exclusiveMinimum, exclusiveMaximum enhancement New feature or request examples python python script changes Review Complexity : High Generally require indepth knowledge of LLMs or GPUs Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level server testing Everything test related
#7797 opened Jun 6, 2024 by ochafik • Draft
3 of 7 tasks
2
WIP: Use DirectStorage with CUDA interop to more efficient load tensors build Compilation issues ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level
#7796 opened Jun 6, 2024 by mtavenrath • Draft
18
feat: add changes to handle jina v2 chinese code python python script changes Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level
#7795 opened Jun 6, 2024 by JoanFM Loading…
18
JSON Schema to GBNF integration tests Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level testing Everything test related
#7790 opened Jun 6, 2024 by HanClinto Loading…
3
Fix missing libgomp.so.1 Error in Docker Container for llama.cpp devops improvements to build systems and github actions Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7775 opened Jun 5, 2024 by 0x4139 Loading…
Enable stream updating in the SwiftUI example examples Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7754 opened Jun 5, 2024 by shu223 Loading…
Fix no gcc pragma on Windows merge ready indicates that this may be ready to merge soon and is just holding out in case of objections Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7751 opened Jun 4, 2024 by jojorne Loading…
[ci] add LLAMA_CURL flags to the prebuilt binaries devops improvements to build systems and github actions Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7747 opened Jun 4, 2024 by Vaibhavs10 Loading…
7
Poro-34B-chat tokenizer support enhancement New feature or request python python script changes Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7713 opened Jun 3, 2024 by ezosa Loading…
4
ProTip! What’s not been updated in a month: updated:<2024-05-12.