Skip to content

Pull requests: huggingface/text-generation-inference

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
Assignee
Filter by who’s assigned
Sort

Pull requests list

Add request parameters to OTel span for /v1/chat/completions endpoint
#3000 opened Feb 7, 2025 by aW3st Loading…
1 of 5 tasks
Putting back the NCCL forced upgrade.
#2999 opened Feb 7, 2025 by Narsil Loading…
5 tasks
Add loop_controls feature to minijinja to handle {% break %}
#2998 opened Feb 7, 2025 by alvarobartt Loading…
2 of 5 tasks
Use kernels from the kernel hub
#2988 opened Feb 3, 2025 by danieldk Loading…
5 tasks
Add 'json_schema' alias to GrammarType.Json
#2982 opened Jan 31, 2025 by aW3st Loading…
2 of 5 tasks
push layer compressed with zstd instead of gzip
#2980 opened Jan 31, 2025 by co42 Loading…
[Backend] Introduce vLLM backend
#2976 opened Jan 31, 2025 by mfuntowicz Loading…
[Backend] Add Llamacpp backend
#2975 opened Jan 31, 2025 by angt Loading…
feat: add initial qwen2.5-vl model and test
#2971 opened Jan 30, 2025 by drbh Loading…
13 tasks done
Improve Transformers support
#2970 opened Jan 30, 2025 by Cyrilvallez Draft
General fixes for tool calling
#2954 opened Jan 24, 2025 by Trofleb Loading…
2 of 4 tasks
Fix tool call response to adhere to OpenAI spec
#2949 opened Jan 24, 2025 by Datta0 Loading…
llava next image encoder to allow un-aligned patch / image sizes
#2936 opened Jan 22, 2025 by jimexist Loading…
5 tasks
Update Dockerfile to use devel image for compatibility
#2848 opened Dec 16, 2024 by YaserJaradeh Loading…
2 of 5 tasks
Enable qwen2vl video
#2756 opened Nov 18, 2024 by drbh Loading…
9 tasks done
[WIP] Add gfx1100 support to AMD pytorch build
#2642 opened Oct 13, 2024 by cazlo Draft
1 of 5 tasks
Add model_load_time metric
#2311 opened Jul 26, 2024 by Edwinhr716 Loading…
2 of 5 tasks
ProTip! Filter pull requests by the default branch with base:main.