bigscience-workshop petals issues

bigscience-workshop / petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

https://petals.dev

MIT License

9.26k stars 526 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Feature Request - Support For VLM's

#616 asmit203 closed 3 weeks ago
0
Create a bash script for the docker image

#615 valentimarco opened 4 weeks ago
0
Performance improving chances in the future

#614 oldcpple opened 2 months ago
1
Mac M3 Any Model crashing

#613 andrew-morris-rgs opened 2 months ago
2
Enhance Logging in RemoteGenerationMixin for Better Debugging

#612 mandlinsarah opened 2 months ago
0
Enhance Speculative Generation with Better Type Hints and Cleaner Code

#611 mandlinsarah opened 2 months ago
0
Question about overlapped serving blocks

#610 jeremyzhangsq opened 3 months ago
0
Error using the local llama3.1 model

#609 CzsGit opened 3 months ago
1
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 peteblank opened 3 months ago
0
Upgrade Pydantic to >= 2.0.0

#607 Vectorrent closed 3 months ago
0
multiple gpu support?

#606 pass-pass-pass opened 4 months ago
0
Pascal family cards support.

#605 akamaus opened 4 months ago
0
Unable to see private swarm contributers on the Health Monitor

#604 Rohit-03 opened 4 months ago
0
Allow torch>=2.3.0

#603 borzunov closed 4 months ago
0
Fix server warnings, update license links and readme

#602 borzunov closed 4 months ago
0
Update hivemind to support torch >= 2.3.0, pydantic >= 2.0

#601 borzunov closed 4 months ago
0
Materialize buffers in get_block_size()

#600 borzunov closed 4 months ago
0
NotImplementedError:

#599 pass-pass-pass closed 4 months ago
1
Added primitives for speculative decoding and tests

#598 xtinkt closed 4 months ago
0
Meta Llama 3.1

#597 apcameron opened 4 months ago
2
Bump transformers to 4.43.1

#596 justheuristic closed 4 months ago
0
[Test PR] set position, run CI

#595 justheuristic closed 4 months ago
0
running inference session with position getter/setter

#594 justheuristic closed 4 months ago
0
[test] run CI tests with JF Llama 160m

#593 justheuristic closed 4 months ago
0
Allow serving llama models with tensor parallel

#592 Jackmin801 opened 4 months ago
2
draft test

#591 xtinkt opened 4 months ago
0
Speculative inference

#590 xtinkt opened 4 months ago
0
Unable to connect to Private Swarm

#589 Rohit-03 closed 4 months ago
1
Add option to rollback inference for a certain number of steps

#588 xtinkt closed 4 months ago
0
Petals doesn't deal with server failure properly

#587 oldcpple opened 5 months ago
4
Donating System Memory?

#586 NavodPeiris opened 5 months ago
1
batch processing/parallel processing

#585 oldcpple opened 5 months ago
1
test

#584 xtinkt closed 5 months ago
0
Update transformers to 4.41.2

#583 xtinkt closed 5 months ago
0
Feature/kan 162 public ip

#582 jmikedupont2 closed 5 months ago
0
System_prompt

#581 EvilSumrak2049 opened 5 months ago
1
Setup and env.example

#580 Bakobiibizo closed 7 months ago
0
Feature/dht1

#579 jmikedupont2 closed 7 months ago
0
LLama-3-70B support

#578 ELigoP closed 7 months ago
3
Restrict PyTorch version to <2.3.0 to resolve import error

#577 Priyanshupareek closed 7 months ago
2
Error with PyTorch 2.3.0: Missing '_refresh_per_optimizer_state' in 'torch.cuda.amp.grad_scaler'

#576 Priyanshupareek closed 7 months ago
0
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 jmikedupont2 closed 7 months ago
2
Fix dummy cache allocation

#574 artek0chumak closed 7 months ago
0
Manual management of shards

#573 nrs-status opened 7 months ago
1
To test 1

#572 jmikedupont2 closed 7 months ago
0
DynamicCache and Beam Search

#571 artek0chumak opened 7 months ago
0
Fix Mixtral-related issues

#570 artek0chumak closed 7 months ago
0
Error trying to raise Mixtral private swarm server

#569 Qessia closed 7 months ago
13
Is there a way to shard a model without downloading it first?

#568 nrs-status closed 8 months ago
2
WIP GCP TPU XLA Build

#567 jmikedupont2 closed 7 months ago
0