-
Notifications
You must be signed in to change notification settings - Fork 9.1k
Pull requests: ggerganov/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
export-lora : throw error if lora is quantized
examples
#9002
opened Aug 12, 2024 by
ngxson
Loading…
2 of 4 tasks
fix: duplication n_predict key in the generation_settings
examples
server
#8994
opened Aug 12, 2024 by
snowyu
Loading…
2 of 4 tasks
llama : support raw NUL bytes in tokens
examples
ggml
changes relating to the ggml tensor library for machine learning
need feedback
Testing and feedback with results are needed
python
python script changes
#8992
opened Aug 12, 2024 by
compilade
Loading…
2 of 5 tasks
feat: whitelist jina bert v2 for llama-server embedding
examples
server
#8989
opened Aug 12, 2024 by
wsxiaoys
Loading…
2 of 4 tasks
server : fix segfault on long system prompt
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
#8987
opened Aug 11, 2024 by
compilade
Loading…
2 tasks done
Revert "ggml : remove OpenCL (#7735) + (#8235)"
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
build
Compilation issues
devops
improvements to build systems and github actions
documentation
Improvements or additions to documentation
examples
ggml
changes relating to the ggml tensor library for machine learning
nix
Issues specific to consuming flake.nix, or generally concerned with ❄ Nix-based llama.cpp deployment
python
python script changes
script
Script related
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
llava: Add ACC OP for GPU acceleration to the Vulkan backend in the L…
examples
ggml
changes relating to the ggml tensor library for machine learning
Vulkan
Issues specific to the Vulkan backend
#8984
opened Aug 11, 2024 by
cyzero-kim
Loading…
2 of 4 tasks
llama : support RWKV v6 models
ggml
changes relating to the ggml tensor library for machine learning
python
python script changes
#8980
opened Aug 11, 2024 by
MollySophia
Loading…
2 tasks done
llama : model-based max number of graph nodes calculation
merge ready
indicates that this may be ready to merge soon and is just holding out in case of objections
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8970
opened Aug 10, 2024 by
nicoboss
Loading…
2 of 4 tasks
support MiniCPM-V-2.6
examples
python
python script changes
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
#8967
opened Aug 10, 2024 by
tc-mb
Loading…
Added support to select GPU using metal on Apple Intel or Apple Silicon using --main-gpu index
Apple Metal
https://en.wikipedia.org/wiki/Metal_(API)
examples
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
#8962
opened Aug 10, 2024 by
ifeanyipossibilities
Loading…
2 of 4 tasks
Vulkan Optimizations and Fixes
bugfix
fixes an issue or bug
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
Vulkan
Issues specific to the Vulkan backend
#8959
opened Aug 9, 2024 by
0cc4m
Loading…
2 of 4 tasks
Fix memory leak in src/llama.cpp
bugfix
fixes an issue or bug
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8958
opened Aug 9, 2024 by
mjtalkiewicz
Loading…
2 of 4 tasks
[WIP] Add integration test for lora adapters
bugfix
fixes an issue or bug
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
testing
Everything test related
Retrieval: Fix Memory Leak in Retrieval Query Handling
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
#8955
opened Aug 9, 2024 by
gtygo
Loading…
2 of 4 tasks
ggml : move rope type enum to ggml.h
ggml
changes relating to the ggml tensor library for machine learning
Nvidia GPU
Issues specific to Nvidia GPUs
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
SYCL
https://en.wikipedia.org/wiki/SYCL - GPU programming language
Vulkan
Issues specific to the Vulkan backend
#8949
opened Aug 9, 2024 by
danbev
Loading…
2 of 4 tasks
fix: Fixes wrong input type for raw_dtype in ggml to gguf scripts
bugfix
fixes an issue or bug
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
#8928
opened Aug 8, 2024 by
farbodbj
Loading…
2 of 4 tasks
Added perplexity metrics for llama 3.1 with different quantization se…
documentation
Improvements or additions to documentation
examples
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8924
opened Aug 8, 2024 by
fedric95
Loading…
1 of 3 tasks
Add Nemotron/Minitron GGUF Conversion & Inference Support
python
python script changes
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
#8922
opened Aug 8, 2024 by
suhara
Loading…
2 of 4 tasks
Quantize: specify each major tensor quant in CLI for common LLMs
demo
Demonstrate some concept or idea, not intended to be merged
examples
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
README: add llama.sh to the available UIs
documentation
Improvements or additions to documentation
Review Complexity : Low
Trivial changes to code that most beginner devs (or those who want a break) can tackle. e.g. UI fix
#8910
opened Aug 7, 2024 by
m18coppola
Loading…
2 of 4 tasks
Introduction of gemm4xN and gemmMx4 for Q4_0 and Q8_0 for better performance results
Review Complexity : Medium
Generally require more time to grok but manageable by beginner to medium expertise level
#8908
opened Aug 7, 2024 by
Srihari-mcw
Loading…
2 of 4 tasks
Previous Next
ProTip!
no:milestone will show everything without a milestone.