Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
Clear current search query, filters, and sorts
579 Open 7,621 Closed
579 Open 7,621 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

metal: template for mat-vec multiplication kernels performance Speed related topics
#2891 opened Aug 30, 2023 by lshzh-ww Loading… updated Sep 15, 2023
29
Don't highlight console session as Java.
#3102 opened Sep 9, 2023 by remexre Loading… updated Sep 15, 2023
2
one can now specify where ggml-metal.metal file is with en variable GGML_METAL_PATH
#2623 opened Aug 15, 2023 by xvolks Loading… updated Sep 15, 2023
ggml : PoC for normalizing weights for better quantization packing demo Demonstrate some concept or idea, not intended to be merged
#2434 opened Jul 28, 2023 by ggerganov • Draft updated Sep 15, 2023
17
Create example bash script for LlaMa 2 Chat
#2408 opened Jul 26, 2023 by lionelchg Loading… updated Sep 15, 2023
Use conversation template for api proxy, fix eventsource format
#2383 opened Jul 25, 2023 by zeyugao Loading… updated Sep 15, 2023
4
Consider adding repo-review badge to README
#2296 opened Jul 20, 2023 by repo-reviews Loading… updated Sep 15, 2023
Llama training finetuning interface
#2246 opened Jul 17, 2023 by howard0su • Draft updated Sep 15, 2023
2
Porting MPI PR to Darwin OpenMPI
#2168 opened Jul 10, 2023 by chadbrewbaker Loading… updated Sep 15, 2023
3
[llama] Add resegment post processing of tokenizer
#2072 opened Jul 2, 2023 by howard0su • Draft updated Sep 15, 2023
6
Avoid allocating beyond MTLDevice.recommendedMaxWorkingSetSize
#2069 opened Jul 2, 2023 by kiltyj • Draft updated Sep 15, 2023
try to fix compile warnings on macOS, address issue #2036
#2037 opened Jun 28, 2023 by mqy Loading… updated Sep 15, 2023
Example work stealing chunked task allocator for issue #291
#2026 opened Jun 27, 2023 by mqy • Draft updated Sep 15, 2023
1
Draft: #1776 making bos and eos available for user input
#1986 opened Jun 24, 2023 by HashemAlsaket • Draft updated Sep 15, 2023
1
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 Loading… updated Sep 15, 2023
6
ci: add linux binaries to release build
#1505 opened May 17, 2023 by Green-Sky Loading… updated Sep 15, 2023
14
Upgrade v1/v2 format to v3 by leveraging quantize
#1504 opened May 17, 2023 by howard0su Loading… updated Sep 15, 2023
29
Implement get_num_physical_cores() for Windows
#1278 opened May 2, 2023 by DannyDaemonic Loading… updated Sep 15, 2023
1
15
fix(LoRA): debugging
#1190 opened Apr 26, 2023 by jon-chuang Loading… updated Sep 15, 2023
3
main: add pledge call on OpenBSD
#1132 opened Apr 22, 2023 by codesoap Loading… updated Sep 15, 2023
llama : quantize attention results demo Demonstrate some concept or idea, not intended to be merged
#1103 opened Apr 21, 2023 by ggerganov • Draft updated Sep 15, 2023
1
@ggerganov
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 Loading… updated Sep 15, 2023
1
Add mmap pages stats (disabled by default)
#1015 opened Apr 16, 2023 by prusnak Loading… updated Sep 15, 2023
1
Run several single thread operators parellel threading Parallel processing and thread management
#850 opened Apr 8, 2023 by howard0su Loading… updated Sep 15, 2023
7
Optimize locking behavior threading Parallel processing and thread management
#813 opened Apr 6, 2023 by janekb04 Loading… updated Sep 15, 2023
19
ProTip! Exclude everything labeled bug with -label:bug.