Skip to content

Pull requests: bigscience-workshop/petals

New pull request New
Clear current search query, filters, and sorts
14 Open 258 Closed
14 Open 258 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Update install instructions to cuda 11.8
#438 opened Aug 6, 2023 by vadi2 Loading…
3
Remove smaller limit for legacy bfloat16 serialization
#505 opened Sep 5, 2023 by borzunov • Draft
1 task
Add loading LoRA adapters from clients' requests
#506 opened Sep 6, 2023 by artek0chumak • Draft
Fix retries during inference
#523 opened Sep 28, 2023 by borzunov • Draft
1
Fix push-docker-image's "No space left on device"
#555 opened Feb 17, 2024 by dvmazur • Draft
mitigate unnecessary swarm rebalancing
#493 opened Aug 31, 2023 by iateadonut Loading…
Forward arbitrary kwargs to remote blocks
#467 opened Aug 17, 2023 by justheuristic Loading…
14 of 27 tasks
6
install script to help the project deployment or for easy use
#544 opened Nov 16, 2023 by elsolo5000-2 Loading…
Example of agents usage with Petals
#547 opened Dec 11, 2023 by RomaA2000 Loading…
replaced call to _prepare_decoder_attention_mask() with _prepare_4d_causal_attention_mask()
#545 opened Nov 21, 2023 by poedator • Draft
1
Direct server-to-server communication during finetuning
#560 opened Mar 9, 2024 by dvmazur • Draft
Llama: Merge query/key/value projection layers
#498 opened Sep 2, 2023 by mryab Loading…
Speculative inference
#590 opened Jul 18, 2024 by xtinkt Loading…
draft test
#591 opened Jul 18, 2024 by xtinkt Loading…
ProTip! Exclude everything labeled bug with -label:bug.