S-LoRA/S-LoRA issues and pull requests

#43 - Dockerfile for creating docker image

Issue - State: open - Opened by FerranAgulloLopez 3 months ago

#42 - Any plans for a llama 3 version?

Issue - State: open - Opened by AWAS666 6 months ago

#41 - any performance testing about S-lora ?

Issue - State: open - Opened by white-wolf-tech 8 months ago

#40 - Can I get a citation

Issue - State: open - Opened by sabetAI 8 months ago

#39 - Failed to run tp branch

Issue - State: open - Opened by sleepwalker2017 9 months ago

#38 - Any advice for debugging this project?

Issue - State: open - Opened by sleepwalker2017 9 months ago

#37 - Get stuck after running benchmark client

Issue - State: open - Opened by sleepwalker2017 9 months ago

#36 - Train using huggingface PEFT & Serve using S-Lora

Issue - State: open - Opened by hchoi-moveworks 10 months ago - 1 comment

#35 - Any performance of llama2-series model?

Issue - State: open - Opened by skykiseki 10 months ago

#34 - Workaround with GPT2

Issue - State: open - Opened by jannikbuscha 10 months ago

#33 - Support qwen?

Issue - State: open - Opened by yinjiaoyuan 10 months ago

#32 - Add fair scheduler VTC

Pull Request - State: closed - Opened by Ying1123 10 months ago

#31 - Query multiple LoRA by weights

Issue - State: open - Opened by authurlord 11 months ago
Labels: good first issue

#30 - Develop quant llama

Pull Request - State: open - Opened by suilin0432 11 months ago

#29 - not support baichuan

Issue - State: open - Opened by codernew007 11 months ago

#28 - Install failed : cuda/pipeline: No such file or directory

Issue - State: open - Opened by oushu1zhangxiangxuan1 11 months ago

#27 - Tensor parallelism with S-LoRA

Issue - State: closed - Opened by debraj135 11 months ago - 1 comment

#26 - When will the Qianwen model be supported?

Issue - State: open - Opened by takemars 11 months ago - 2 comments

#25 - Does it support V100 GPU?

Issue - State: open - Opened by Ted8000 11 months ago - 2 comments

#24 - Multi-GPU Support

Issue - State: open - Opened by luciferlinx101 11 months ago - 1 comment
Labels: good first issue

#23 - ISSUE

Issue - State: closed - Opened by sailakkshmiallada 12 months ago - 1 comment

#22 - What's the difference from LoRAX

Issue - State: closed - Opened by wDevil 12 months ago - 2 comments

#21 - Question about device bandwidth

Issue - State: open - Opened by qizzzh 12 months ago

#20 - Support chatglm3 ?

Issue - State: open - Opened by litetoooooom 12 months ago

#19 - ModuleNotFoundError: No module named 'slora._kernels'

Issue - State: open - Opened by yaoshao123 12 months ago - 3 comments

#18 - Encountered some problems when adding the support for GPT-Q 4-bit quantized LLaMA-2 model.

Issue - State: closed - Opened by suilin0432 12 months ago - 2 comments

#17 - Encoder-Decoder model support

Issue - State: open - Opened by aravindMahadevan 12 months ago

#16 - Support for GPT-NEOX models

Issue - State: open - Opened by bibekyess 12 months ago

#15 - AttributeError: 'LoraLayerWeight' object has no attribute 'k_lora_A_home'

Issue - State: open - Opened by raihan0824 12 months ago - 2 comments

#14 - how the finetune works, does it support peft lora?

Issue - State: open - Opened by whybeyoung 12 months ago

#13 - add tips for install from source or we will get error from cuda

Pull Request - State: closed - Opened by whitelok 12 months ago

#12 - Choosing adapters on inference

Issue - State: closed - Opened by raihan0824 12 months ago - 2 comments

#11 - can it support rtx 4090 (24 gb) ?

Issue - State: open - Opened by jaiabhayk 12 months ago - 1 comment

#10 - Question about cuda kernel

Issue - State: closed - Opened by harryhan618 12 months ago - 2 comments

#9 - OpenAI API webserver compatible

Issue - State: open - Opened by giaosudau 12 months ago
Labels: good first issue

#8 - torch 2.0.1 requires triton==2.0.0

Issue - State: closed - Opened by giaosudau 12 months ago - 1 comment

#7 - Potential issue related to Python's early-bound default parameters

Issue - State: open - Opened by bugface 12 months ago

#6 - Quantisation

Issue - State: open - Opened by nivibilla 12 months ago

#5 - Add clickable link to corresponding Arxiv article

Issue - State: closed - Opened by impredicative about 1 year ago - 1 comment

#4 - Update installation docs: Add recommend GPUs, make CUDA conda inst...

Pull Request - State: closed - Opened by Muhtasham about 1 year ago - 1 comment

#3 - Mistral

Issue - State: open - Opened by bacoco about 1 year ago - 3 comments
Labels: good first issue

#2 - This is huge!

Issue - State: closed - Opened by yhyu13 about 1 year ago - 5 comments

#1 - add hf load utils

Pull Request - State: closed - Opened by caoshiyi about 1 year ago

GitHub / S-LoRA/S-LoRA issues and pull requests