evilsocket/cake
Distributed LLM and StableDiffusion inference for mobile, desktop and server.
RustNOASSERTION
Issues
- 0
build error on compiling with cuda features
#29 opened by venusarathy - 0
request for the second time error details
#26 opened by ddbbcc - 0
- 3
- 0
- 1
May I ask why I am unable to download the model and use the product through Huggingface
#23 opened by Caesarleee - 6
Is it possible to use quantized models?
#22 opened by ManuXD32 - 3
Standardized Android client
#14 opened by TriDefender - 2
Dockerfile support
#12 opened by James4Ever0 - 3
Req Support for Llama 3.1
#21 opened by jkfnc - 5
- 3
- 4
bug with tokenizer and gibberish output
#9 opened by evilsocket - 2
Thanks for the FOSS! Suggestion for future possible backends runtimes: Vulkan, OpenCL, SYCL/OpenVino/intel GPU, AMD gpu/ROCm/HIP.
#20 opened by ghchris2021 - 2
Unable to build without CUDA
#16 opened by damnkrat - 1
Use hf_hub crate to pull model
#15 opened by b0xtch - 3
About the reason of having cluster nodes
#10 opened by hafezmg48 - 4
PTX代码使用了一个不被支持的工具链进行编译
#11 opened by JKYtydt - 9
- 1
- 1
- 2
Cross-device mapping
#2 opened by b0xtch - 3