Skip to content

Pull requests: ggerganov/llama.cpp

New pull request New
271 Open 3,953 Closed
271 Open 3,953 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

baby-llama : rename llama_layer to baby_llama_layer examples
#9557 opened Sep 20, 2024 by danbev Loading…
2 of 4 tasks
1
Update CUDA graph on scale change plus clear nodes/params Nvidia GPU Issues specific to Nvidia GPUs
#9550 opened Sep 19, 2024 by agray3 Loading…
1 of 3 tasks
1
1
server: disable context shift examples server
#9544 opened Sep 19, 2024 by VJHack • Draft
2 of 4 tasks
1
add solar pro support python python script changes
#9541 opened Sep 18, 2024 by mxyng Loading…
2 of 4 tasks
1
Implementations for Q4_0_8_8 quantization based functions - AVX512 version of ggml_gemm_q4_0_8x8_q8_0 ggml changes relating to the ggml tensor library for machine learning
#9532 opened Sep 18, 2024 by Srihari-mcw Loading…
2 of 4 tasks
1
musa: enable building fat binaries, enable VMM support, and disable Flash Attention on QY1 (MTT S80) Nvidia GPU Issues specific to Nvidia GPUs
#9526 opened Sep 18, 2024 by yeahdongcn Loading…
5 of 7 tasks
7
llama: (proposal) propagating the results of graph_compute to the user interface
#9525 opened Sep 17, 2024 by Xarbirus Loading…
2 of 4 tasks
2
docs: update server streaming mode documentation examples server
#9519 opened Sep 17, 2024 by CentricStorm Loading…
2 of 4 tasks
1
llama : add reranking support examples python python script changes server
#9510 opened Sep 16, 2024 by ggerganov • Draft
3 tasks
2
Update clip.cpp examples
#9482 opened Sep 14, 2024 by Tejaakshaykumar Loading…
2 of 4 tasks
8
CI: Provide prebuilt windows binary for hip devops improvements to build systems and github actions
#9467 opened Sep 13, 2024 by no1wudi Loading…
2 of 4 tasks
3
RWKV v6: RWKV_WKV op CUDA implementation Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#9454 opened Sep 12, 2024 by MollySophia Loading…
4 tasks done
2
vocab: refactor tokenizer to reduce the overhead of creating multi times tokenizer
#9449 opened Sep 12, 2024 by kylo5aby Loading…
4 of 6 tasks
11
IBM Granite MoE Architecture python python script changes
#9438 opened Sep 11, 2024 by gabe-l-hart Loading…
3 of 5 tasks
3
vulkan : do not use tensor->extra ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#9407 opened Sep 10, 2024 by rgerganov Loading…
2 of 4 tasks
1
naming : normalize the name of callback-related identifiers Apple Metal https://en.wikipedia.org/wiki/Metal_(API) breaking change Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility. examples ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#9405 opened Sep 10, 2024 by ggerganov Loading…
1
feat: support internvl examples python python script changes
#9403 opened Sep 10, 2024 by qlylangyu Loading…
2 of 4 tasks
1
imatrix : use GGUF to store importance matrices breaking change Changes that break ABIs, APIs, file formats, or other forms of backwards compatibility. enhancement New feature or request examples python python script changes refactoring Refactoring Review Complexity : Medium Generally require more time to grok but manageable by beginner to medium expertise level
#9400 opened Sep 10, 2024 by compilade • Draft
3 of 8 tasks
5
convert : refactor rope_freqs generation bugfix fixes an issue or bug python python script changes 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
#9396 opened Sep 10, 2024 by compilade Loading…
6 of 10 tasks
9
ggml: Add run-time detection of neon, i8mm and sve ggml changes relating to the ggml tensor library for machine learning
#9331 opened Sep 6, 2024 by eddnjjn Loading…
2 of 4 tasks
3
ggml/kompute: Add multi-GPU support ggml changes relating to the ggml tensor library for machine learning Kompute https://github.com/KomputeProject/kompute/
#9328 opened Sep 6, 2024 by flynnjiang Loading…
2 of 4 tasks
2
cmake : use ggml-metal.metal from source dir to build default.metallib
#9325 opened Sep 5, 2024 by cebtenzzre Loading…
2 of 4 tasks
1
server : add Hermes-3 tool call support (WIP) examples server
#9254 opened Aug 30, 2024 by ngxson • Draft
7 of 12 tasks
1
5
Enable use to the rebar feature to upload buffers to the device. 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 Vulkan Issues specific to the Vulkan backend
#9251 opened Aug 30, 2024 by mtavenrath Loading…
2 of 4 tasks
1
metadata: Allow model creators to use modelcard datasets and base_model as a list of dicts 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
#9221 opened Aug 28, 2024 by mofosyne • Draft
2 of 4 tasks
1
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.