The Wayback Machine - https://web.archive.org/web/20230723080637/https://github.com/bigscience-workshop/petals/issues
Skip to content

Issues: bigscience-workshop/petals

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

48 Open 61 Closed
48 Open 61 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇄1�7 + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Expand on FLUX network of decentralized nodes
#408 opened Jul 23, 2023 by mongolu
Two Issues: Downloading entire model + Attempt to start a new process before current process finished
#405 opened Jul 22, 2023 by mberman84
2
Add windows support
#400 opened Jul 21, 2023 by dinosaurtirex
5
Petals Error: GPU is not available
#398 opened Jul 21, 2023 by SephReed
1
Allow filtering by max sequence length
#394 opened Jul 20, 2023 by justheuristic
2
Swarm balancing logic issues
#389 opened Jul 20, 2023 by fadenb
1
Implemented FlashAttention 2
#387 opened Jul 20, 2023 by Jeduh
@mryab
2
Reachability service occasionally fails
#376 opened Jul 19, 2023 by borzunov
rpc_push may fail due to exceeding max message size
#372 opened Jul 19, 2023 by justheuristic
How to upload to hub and use model later on?
#367 opened Jul 18, 2023 by ryanshrott
1
Add LogitsProcessing in generative pipeline.
#361 opened Jul 17, 2023 by artek0chumak
@artek0chumak
Speed up loading blocks using safetensors
#347 opened Jul 13, 2023 by borzunov
Add tests for LLaMA, int8, nf4
#338 opened Jul 3, 2023 by borzunov
3 tasks
Repeated missingblockserror
#328 opened Jun 14, 2023 by hazelsilver8740
Prompt Tuning met NaN error
#327 opened Jun 13, 2023 by xinghua-qu
1
1
Petals.server.handler connects to peer_id timeout.
#326 opened Jun 11, 2023 by dev-null-2140
How to specify lora parameters
#322 opened Jun 4, 2023 by 01miaom
how to load model with torch_dtype='float32' in petals?
#321 opened Jun 1, 2023 by amitbiswas1999
1
Loading LoRA weights
#320 opened May 27, 2023 by karim1104
Running bloom-chat on petals
#318 opened May 25, 2023 by barsuna
4
Facing Issue while running 176b bloom-petals model
#317 opened May 11, 2023 by Likhith07
Allocate all GPU memory on startup help wanted Collaborators needed
#308 opened Apr 24, 2023 by borzunov
Ensure that SequenceManager is thread-safe
#303 opened Apr 12, 2023 by borzunov
Is it possible to share DistributedBloomForCausalLM between several worker processes?
#296 opened Mar 27, 2023 by arikon
5
Create a user-friendly Windows installer
#289 opened Mar 12, 2023 by worldpeaceenginelabs
2
ProTip! Add no:assignee to see everything that’s not assigned.