-
Notifications
You must be signed in to change notification settings - Fork 8.5k
Pull requests: ggerganov/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
convert-hf : set the model name based on cli arg, if present
python
python script changes
#7693
opened Jun 2, 2024 by
sasha0552
Loading…
chore: Add ignore rule for generated server themes
#7689
opened Jun 2, 2024 by
teleprint-me
Loading…
convert-hf : match model part name prefix and suffix
bugfix
fixes an issue or bug
merging soon
Will merge soon unless anyone objects
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
#7687
opened Jun 2, 2024 by
compilade
Loading…
nix: update flake.lock
nix
Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
#7686
opened Jun 2, 2024 by
ggerganov
Loading…
Per token attributes
python
python script changes
testing
Everything test related
#7685
opened Jun 1, 2024 by
jaime-m-p
Loading…
CUDA: use tensor cores for MMQ
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
#7676
opened May 31, 2024 by
JohannesGaessler
•
Draft
common : refactor cli arg parsing
examples
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
docs: repeat-penalty 1.0 = disabled
examples
merging soon
Will merge soon unless anyone objects
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7669
opened May 31, 2024 by
brandon-lockaby
Loading…
MiniCPM Support lm_head
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
#7664
opened May 31, 2024 by
zkh2016
Loading…
llama : avoid double token-to-piece cache
review complexity : medium
Generally require more time to grok but manageable by beginner to medium expertise level
#7654
opened May 30, 2024 by
ggerganov
Loading…
Merging #7568 with #7430(Implementing LLaMA 3 torch to gguf conversion)
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
#7651
opened May 30, 2024 by
Manaball123
Loading…
fix: change first msg check
bugfix
fixes an issue or bug
examples
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
server
#7649
opened May 30, 2024 by
ryan1117001
Loading…
Only use FIM middle token if it exists
examples
merging soon
Will merge soon unless anyone objects
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
server
#7648
opened May 30, 2024 by
CISC
Loading…
llama_supports_rpc()
function
merging soon
#7647
opened May 30, 2024 by
martindevans
Loading…
More checks before assuming FIM tokens for Llama arch
bugfix
fixes an issue or bug
medium severity
Used to report medium severity bugs in llama.cpp (e.g. Malfunctioning Features but still useable)
merging soon
Will merge soon unless anyone objects
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7644
opened May 30, 2024 by
CISC
Loading…
Catch exceptions correctly in server.cpp
bugfix
fixes an issue or bug
examples
high severity
Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
merging soon
Will merge soon unless anyone objects
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
server
#7642
opened May 30, 2024 by
0wwafa
Loading…
llama : offload to RPC in addition to other backends
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
#7640
opened May 30, 2024 by
rgerganov
Loading…
ggml : unify rope norm/neox
examples
ggml
changes relating to the ggml tensor library for machine learning
Kompute
https://github.com/KomputeProject/kompute/
Nvidia GPU
Issues specific to Nvidia GPUs
python
python script changes
refactoring
Refactoring
review complexity : high
Generally require indepth knowledge of LLMs or GPUs
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
testing
Everything test related
Vulkan
Issues specific to the Vulkan backend
#7634
opened May 30, 2024 by
ggerganov
Loading…
8 of 11 tasks
Vulkan Mixture of Experts (MoE) support
python
python script changes
review complexity : high
Generally require indepth knowledge of LLMs or GPUs
Vulkan
Issues specific to the Vulkan backend
#7628
opened May 29, 2024 by
0cc4m
Loading…
Readme: add HyperMink/inferenceable to HTTP server
review complexity : low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#7607
opened May 29, 2024 by
sameercharles
Loading…
ggml: Support OpenMP for multi-thread processing
build
Compilation issues
devops
improvements to build systems and github actions
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
#7606
opened May 29, 2024 by
msy-kato
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…
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
Previous Next
ProTip!
Updated in the last three days: updated:>2024-05-30.