Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
Clear current search query, filters, and sorts
404 Open 5,223 Closed
404 Open 5,223 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
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

Add CFG to server
#2217 opened Jul 13, 2023 by SlyEcho • Draft
1 of 4 tasks
10 😄 7
Add support for Deepseek-R1 flash attention ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#11557 opened Jan 31, 2025 by siddartha-RE • Review required
6 😄 6
llama : support Jamba hybrid Transformer-Mamba models android Issues specific to Android embeddings embedding related topics enhancement New feature or request examples ggml changes relating to the ggml tensor library for machine learning model Model specific need feedback Testing and feedback with results are needed python python script changes refactoring Refactoring Review Complexity : High Generally require indepth knowledge of LLMs or GPUs server
#7531 opened May 25, 2024 by compilade • Draft
7 of 17 tasks
1
31 😄 4
Q4_0 scale selection using RMSE enhancement New feature or request Less than 4 bits Efforts related to viable quantized models using <4 bits research 🔬 Review Complexity : High Generally require indepth knowledge of LLMs or GPUs
#835 opened Apr 7, 2023 by sw • Draft
1
@sw
14
Run several single thread operators parellel threading Parallel processing and thread management
#850 opened Apr 8, 2023 by howard0su • Review required
7
Use Threadpool to schedule the work threading Parallel processing and thread management
#851 opened Apr 8, 2023 by howard0su • Draft
9
Add mmap pages stats (disabled by default)
#1015 opened Apr 16, 2023 by prusnak • Review required
1
Add command mode to interactive mode. enhancement New feature or request Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level
#1022 opened Apr 17, 2023 by wbpxre150 • Review required
2
Add a option to force the token end of text apears even on interative, and also shows loading porcentage
#1058 opened Apr 19, 2023 by jeffersoncgo • Review required
1
llama : quantize attention results demo Demonstrate some concept or idea, not intended to be merged
#1103 opened Apr 21, 2023 by ggerganov • Draft
1
@ggerganov
llama : add llama_set_attn_type API examples
#12615 opened Mar 27, 2025 by ngxson • Review required
1
4
fix(LoRA): debugging
#1190 opened Apr 26, 2023 by jon-chuang • Review required
3
Getting started documentation
#1198 opened Apr 26, 2023 by TheNotary • Review required
16
Create run.py enhancement New feature or request obsolete? Marker for potentially obsolete PR 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 script Script related
#1204 opened Apr 27, 2023 by jdpsl • Review required
1
Add "-e"/"--eval-threads" to distinguish thread counts for single-token eval and prompt eval threading Parallel processing and thread management
#744 opened Apr 3, 2023 by MagisterLuddite • Draft
10
[Research] Steering vectors research 🔬
#1472 opened May 16, 2023 by SlyEcho • Draft
62
Upgrade v1/v2 format to v3 by leveraging quantize
#1504 opened May 17, 2023 by howard0su • Review required
29
ggml : spread compute across threads in chunks demo Demonstrate some concept or idea, not intended to be merged threading Parallel processing and thread management
#1507 opened May 17, 2023 by ggerganov • Review required
6
Llama cpp low level python bindings
#1660 opened Jun 1, 2023 by dmahurin • Review required
4
Added Arbitrary mixed quantization Less than 4 bits Efforts related to viable quantized models using <4 bits research 🔬
#1834 opened Jun 13, 2023 by Milkdrop • Review required
6
Disable _O_WTEXT when using main in MinGW
#1897 opened Jun 16, 2023 by asctime • Review required
Example work stealing chunked task allocator for issue #291
#2026 opened Jun 27, 2023 by mqy • Draft
1
Avoid unused constant warnings refactoring Refactoring Review Complexity : Low Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#2029 opened Jun 28, 2023 by set-soft • Review required
3
try to fix compile warnings on macOS, address issue #2036
#2037 opened Jun 28, 2023 by mqy • Review required
Implement get_num_physical_cores() for Windows
#1278 opened May 2, 2023 by DannyDaemonic • Review required
1
15
ProTip! Add no:assignee to see everything that’s not assigned.