Skip to content

Pull requests: huggingface/text-generation-inference

New pull request New
14 Open 851 Closed
14 Open 851 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

PR #2049 CI run
#2054 opened Jun 11, 2024 by drbh Loading…
Add support for GPTQ Marlin
#2052 opened Jun 11, 2024 by danieldk • Draft
5 tasks
Use minijinja's pycompat mode for python methods
#2049 opened Jun 11, 2024 by mitsuhiko Loading…
2 of 5 tasks
1
use xpu-smi to dump used memory
#2047 opened Jun 11, 2024 by sywangyi Loading…
5 tasks
2
Adding architecture document
#2044 opened Jun 10, 2024 by tengomucho Loading…
1
Enabling CI for AMD with new runner..
#2034 opened Jun 6, 2024 by Narsil Loading…
5 tasks
[WIP] Add kvcache fp8 support
#2028 opened Jun 6, 2024 by mht-sharma • Draft
22
feat: re-allocate pages dynamically
#2024 opened Jun 5, 2024 by OlivierDehaene Loading…
19
Enable multiple LoRa adapters
#2010 opened Jun 4, 2024 by drbh Loading…
10
Split build workflow for multiple plateforms
#2005 opened Jun 4, 2024 by fxmarty Loading…
2
implement Open Inference Protocol endpoints
#1942 opened May 23, 2024 by drbh Loading…
7
[Major Change][Undecided yet] Move to FlashDecoding instead of PagedAttention kernel.
#1940 opened May 23, 2024 by Narsil Loading…
5 tasks
2
Cpu tgi
#1936 opened May 23, 2024 by sywangyi Loading…
5 tasks
10
add ascend npu support for TGI Stale
#1740 opened Apr 14, 2024 by statelesshz • Draft
5 tasks
ProTip! no:milestone will show everything without a milestone.