-
Notifications
You must be signed in to change notification settings - Fork 8.4k
Pull requests: ggerganov/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
github: add contact links to issues and convert question into researc…
devops
improvements to build systems and github actions
#7612
opened May 29, 2024 by
mofosyne
Loading…
cuda : non-cont concat support
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
testing
Everything test related
#7610
opened May 29, 2024 by
ggerganov
Loading…
Readme: add HyperMink/inferenceable to HTTP server
#7607
opened May 29, 2024 by
sameercharles
Loading…
fix Visual Studio 17.10 internal compiler error on redefinition stati…
bugfix
fixes an issue or bug
build
Compilation issues
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
#7604
opened May 29, 2024 by
HungMingWu
Loading…
support MiniCPM-V-2.5
examples
python
python script changes
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
#7599
opened May 28, 2024 by
tc-mb
Loading…
ggml : use atomic_flag for critical section
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
#7598
opened May 28, 2024 by
slaren
Loading…
feat: add changes to handle jina v2 base code
python
python script changes
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
llama : cache llama_token_to_piece
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7587
opened May 28, 2024 by
ggerganov
Loading…
vulkan: select only one device for single gpu with multiple drivers
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
Vulkan
Issues specific to the Vulkan backend
#7582
opened May 28, 2024 by
Adriankhl
Loading…
batched : make n_threads and n_threads_batch configurable in batched & batched-bench
examples
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
#7581
opened May 28, 2024 by
msy-kato
Loading…
ggml-threading.cpp
build
Compilation issues
ggml
changes relating to the ggml tensor library for machine learning
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
distributed evaluation with speculation demo v0
examples
ggml
changes relating to the ggml tensor library for machine learning
performance
Speed related topics
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
#7570
opened May 27, 2024 by
okuvshynov
•
Draft
Made convert.py work with LLaMA 3 files distributed by meta
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
#7568
opened May 27, 2024 by
Manaball123
Loading…
fix performance regression on woa
build
Compilation issues
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7555
opened May 27, 2024 by
ReinForce-II
Loading…
Add PaliGemma Support
examples
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
faster avx512 exp implementation
ggml
changes relating to the ggml tensor library for machine learning
performance
Speed related topics
refactoring
Refactoring
review complexity : high
Generally require indepth knowledge of LLMs or GPUs
#7551
opened May 27, 2024 by
chriselrod
Loading…
SimpleChat: Simple histogram and repeat matching driven garbage trimming, Settings UI, Streaming mode support
examples
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
server
Feat: Support of converting local models added to 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
convert-hf-to-gguf-update.py
python
#7547
opened May 26, 2024 by
EvilFreelancer
Loading…
ggml : fix loongson compile warnings
ggml
changes relating to the ggml tensor library for machine learning
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
Portability: use the ccache path detected in cmake when setting the compiler launch rule
build
Compilation issues
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7535
opened May 25, 2024 by
s-daveb
Loading…
llama : support Jamba hybrid Transformer-Mamba models
embeddings
embedding related topics
enhancement
New feature or request
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
Tokenizer BPE fixes
python
python script changes
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
testing
Everything test related
#7530
opened May 25, 2024 by
jaime-m-p
Loading…
7 of 10 tasks
CUDA: quantized KV support for FA vec
build
Compilation issues
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
review complexity : high
Generally require indepth knowledge of LLMs or GPUs
testing
Everything test related
#7527
opened May 24, 2024 by
JohannesGaessler
Loading…
Previous Next
ProTip!
no:milestone will show everything without a milestone.