Skip to content

Pull requests: huggingface/text-generation-inference

New pull request New
29 Open 1,463 Closed
29 Open 1,463 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

dockerfile change to ipex cpu/xpu
#3013 opened Feb 11, 2025 by sywangyi Loading…
Fix CPU and memory affinity under external resource management
#3012 opened Feb 11, 2025 by askervin Loading…
1
fix: update expected output from town to village
#3010 opened Feb 11, 2025 by drbh Loading…
Pr 3002 ci branch
#3008 opened Feb 10, 2025 by drbh Loading…
1
Pr 3003 ci branch
#3007 opened Feb 10, 2025 by drbh Loading…
Pr 2954 ci branch
#3006 opened Feb 10, 2025 by drbh Loading…
1
fix qwen2 vl crash in continous batching
#3004 opened Feb 10, 2025 by sywangyi Loading…
1
change ChatCompletionChunk to align with "OpenAI Chat Completions str…
#3003 opened Feb 10, 2025 by sywangyi Loading…
3
fix Qwen VL break in intel platform
#3002 opened Feb 10, 2025 by sywangyi Loading…
2
It's find in some machine. using hf_hub::api::sync::Api to download c…
#3001 opened Feb 8, 2025 by sywangyi Loading…
2
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
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…
15
feat: add initial qwen2.5-vl model and test
#2971 opened Jan 30, 2025 by drbh Loading…
13 tasks done
1
Improve Transformers support
#2970 opened Jan 30, 2025 by Cyrilvallez • Draft
Kvrouter that will increase the kv-cache hits in case of multiple routing strategy
#2965 opened Jan 29, 2025 by Narsil Loading…
5 tasks
1
misc(gha): expose action cache url and runtime as secrets
#2964 opened Jan 29, 2025 by mfuntowicz Loading…
8
General fixes for tool calling
#2954 opened Jan 24, 2025 by Trofleb Loading…
2 of 4 tasks
11
Fix tool call response to adhere to OpenAI spec
#2949 opened Jan 24, 2025 by Datta0 Loading…
@drbh
llava next image encoder to allow un-aligned patch / image sizes
#2936 opened Jan 22, 2025 by jimexist Loading…
5 tasks
4
Update Dockerfile to use devel image for compatibility
#2848 opened Dec 16, 2024 by YaserJaradeh Loading…
2 of 5 tasks
10
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.