S-LoRA/S-LoRA

Issues

• Any plans for a llama 3 version?

  #42 opened 25 days ago by AWAS666
  0

• any performance testing about S-lora ?

  #41 opened 2 months ago by x-transformers
  0

• Can I get a citation

  #40 opened 3 months ago by sabetAI
  0

• Failed to run tp branch

  #39 opened 3 months ago by sleepwalker2017
  0

• Any advice for debugging this project?

  #38 opened 3 months ago by sleepwalker2017
  0

• Get stuck after running benchmark client

  #37 opened 3 months ago by sleepwalker2017
  0

• Train using huggingface PEFT & Serve using S-Lora

  #36 opened 4 months ago by hchoi-moveworks
  0

• ModuleNotFoundError: No module named 'slora._kernels'

  #19 opened 6 months ago by yaoshao123
  3

• Any performance of llama2-series model?

  #35 opened 4 months ago by skykiseki
  0

• Workaround with GPT2

  #34 opened 4 months ago by jannikbuscha
  0

• Support qwen?

  #33 opened 5 months ago by yinjiaoyuan
  0

• When will the Qianwen model be supported?

  #26 opened 6 months ago by takemars
  1

• OpenAI API webserver compatible

  #9 opened 6 months ago by giaosudau
  0

• Mistral

  #3 opened 7 months ago by bacoco
  3

• Multi-GPU Support

  #24 opened 6 months ago by luciferlinx101
  1

• Query multiple LoRA by weights

  #31 opened 5 months ago by authurlord
  0

• Does it support V100 GPU?

  #25 opened 6 months ago by Ted8000
  2

• not support baichuan

  #29 opened 5 months ago by codernew007
  0

• Install failed : cuda/pipeline: No such file or directory

  #28 opened 5 months ago by oushu1zhangxiangxuan1
  0

• Tensor parallelism with S-LoRA

  #27 opened 5 months ago by debraj135
  1

• What's the difference from LoRAX

  #22 opened 6 months ago by wDevil
  2

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

  #18 opened 6 months ago by suilin0432
  2

• ISSUE

  #23 opened 6 months ago by sailakkshmiallada
  1

• Question about device bandwidth

  #21 opened 6 months ago by qizzzh
  0

• AttributeError: 'LoraLayerWeight' object has no attribute 'k_lora_A_home'

  #15 opened 6 months ago by raihan0824
  2

• This is huge!

  #2 opened 6 months ago by yhyu13
  5

• Support chatglm3 ?

  #20 opened 6 months ago by litetoooooom
  0

• Choosing adapters on inference

  #12 opened 6 months ago by raihan0824
  2

• can it support rtx 4090 (24 gb) ?

  #11 opened 6 months ago by jaiabhayk
  1

• Question about cuda kernel

  #10 opened 6 months ago by harryhan618
  2

• Encoder-Decoder model support

  #17 opened 6 months ago by aravindMahadevan
  0

• Support for GPT-NEOX models

  #16 opened 6 months ago by bibekyess
  0

• how the finetune works, does it support peft lora?

  #14 opened 6 months ago by whybeyoung
  0

• torch 2.0.1 requires triton==2.0.0

  #8 opened 6 months ago by giaosudau
  1

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

  #7 opened 6 months ago by bugface
  0

• Quantisation

  #6 opened 7 months ago by nivibilla
  0

• Add clickable link to corresponding Arxiv article

  #5 opened 7 months ago by impredicative
  1