bigscience-workshop/petals

Issues

• Feature Request - Support For VLM's

  #616 opened 19 days ago by asmit203
  0

• Create a bash script for the docker image

  #615 opened 24 days ago by valentimarco
  0

• Error using the local llama3.1 model

  #609 opened 3 months ago by CzsGit
  1

• Performance improving chances in the future

  #614 opened 2 months ago by oldcpple
  1

• Mac M3 Any Model crashing

  #613 opened 2 months ago by andrew-morris-rgs
  2

• Question about overlapped serving blocks

  #610 opened 3 months ago by jeremyzhangsq
  0

• attention_mask = FalconModel._prepare_attn_mask(attention_mask, (batch_size, seq_length), past_length) AttributeError: type object 'FalconModel' has no attribute '_prepare_attn_mask'

  #608 opened 3 months ago by peteblank
  0

• Error when trying to launch private swarm using locally stored model

  #549 opened a year ago by sdryluth
  1

• multiple gpu support?

  #606 opened 4 months ago by pass-pass-pass
  0

• Pascal family cards support.

  #605 opened 4 months ago by akamaus
  0

• Unable to connect to Private Swarm

  #589 opened 4 months ago by Rohit-03
  1

• Unable to see private swarm contributers on the Health Monitor

  #604 opened 4 months ago by Rohit-03
  0

• Meta Llama 3.1

  #597 opened 4 months ago by apcameron
  2

• NotImplementedError:

  #599 opened 4 months ago by pass-pass-pass
  1

• Petals doesn't deal with server failure properly

  #587 opened 5 months ago by oldcpple
  4

• batch processing/parallel processing

  #585 opened 5 months ago by oldcpple
  1

• Manual management of shards

  #573 opened 7 months ago by nrs-status
  1

• Donating System Memory?

  #586 opened 5 months ago by NavodPeiris
  1

• Feature Request: Distributed inference API where the "miners" are paid.

  #556 opened 9 months ago by NewtonTrendy
  2

• System_prompt

  #581 opened 6 months ago by EvilSumrak2049
  1

• LLama-3-70B support

  #578 opened 7 months ago by ELigoP
  3

• Error with PyTorch 2.3.0: Missing '_refresh_per_optimizer_state' in 'torch.cuda.amp.grad_scaler'

  #576 opened 7 months ago by Priyanshupareek
  0

• Error trying to raise Mixtral private swarm server

  #569 opened 7 months ago by Qessia
  13

• RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument tensors in method wrapper_CUDA_cat)

  #575 opened 7 months ago by jmikedupont2
  2

• Latest bump "Bump transformers and accelerate versions (#554)" looks to destroy Falcon support.

  #565 opened 8 months ago by STEMBytes
  5

• Is there any plan to support MoE models like Mixtral8×7B?

  #548 opened 7 months ago by arronKler
  5

• DynamicCache and Beam Search

  #571 opened 7 months ago by artek0chumak
  0

• compile to webassembly

  #566 opened 8 months ago by Donovoi
  3

• Is there a way to shard a model without downloading it first?

  #568 opened 8 months ago by nrs-status
  2

• Grok | Mixture-of-Experts | Model Support

  #564 opened 8 months ago by tibrezus
  3

• Can not use direct server-to-server communication

  #550 opened 8 months ago by miaoqijun
  6

• Reachability issue while connecting to private swarm

  #562 opened 8 months ago by CherukupalleNaveen
  1

• content of 'labels' when doing prompt tuning of llama-2 on QA

  #561 opened 8 months ago by caochuxueeee
  0

• Reachability Issue for private swarm

  #551 opened 9 months ago by VarunJoshi10
  1

• I confirm Petals not working in Google Colab

  #534 opened a year ago by AIAnytime
  2

• Add "Podman" usage to the documentation

  #546 opened a year ago by metal3d
  0

• ImportError: cannot import name 'AutoDistributedModelForCausalLM' from partially initialized module 'petals' (most likely due to a circular import)

  #542 opened a year ago by lacksfish
  3

• Prepull model data on private swarm

  #541 opened a year ago by wolfganghuse
  5

• M1 macOS installation error ("failed to build wheel for hivemind") with mac-native petals

  #540 opened a year ago by MinaAlmasi
  2

• Upstream Changes makes the demo not work

  #536 opened a year ago by hrQAQ
  2

• IndexError: tuple index out of range

  #532 opened a year ago by jaskirat8
  7

• Error while hosting as provider

  #533 opened a year ago by filopedraz
  0

• text to video generation models ?

  #529 opened a year ago by scenaristeur
  2

• Pyinstaller packaged Petals binary fails to load/download on`AutoDistributedModelForCausalLM.from_pretrained`

  #528 opened a year ago by biswaroop1547
  0

• support quivr or privateGPT?

  #524 opened a year ago by lbgws2
  2

• whether past_key_values can be obtained

  #526 opened a year ago by sa1utyeggs
  1

• Add mistral to chat.petals

  #527 opened a year ago by AmgadHasan
  1

• Add pre-commit hook

  #522 opened a year ago by mahimairaja
  0

• Available Models?

  #521 opened a year ago by jontstaz
  1

• Support stable diffusion model

  #519 opened a year ago by lbgws2
  2