Skip to content

Pull requests: huggingface/text-embeddings-inference

New pull request New
48 Open 378 Closed
48 Open 378 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Cuda flake fix
#913 opened Aug 10, 2026 by banderlog Loading…
Fix build via nix-shell
#912 opened Aug 10, 2026 by banderlog Loading…
Add OTLP over HTTP/protobuf export support
#910 opened Aug 4, 2026 by AmreshSinha Loading…
5 tasks
1
docs: note OpenAI client base_url for multi-model gateways
#905 opened Aug 3, 2026 by seven7763 Loading…
3 tasks
Add SigLIP model - text embeddings only
#903 opened Jul 28, 2026 by m-toman • Draft
4 of 5 tasks
Add BAAI/bge-m3 sparse (lexical_weights) support via --pooling m3_sparse
#899 opened Jul 18, 2026 by SpongeRobert Loading…
Speed up ModernBERT inference by 1.15x on CUDA
#897 opened Jul 11, 2026 by hotchpotch Loading…
2 of 4 tasks
v1.9.4
8
docs: warn that cuda-1.9 image + flash-attn silently produces NaN embeddings on Turing/T4
#896 opened Jul 10, 2026 by moduvoice Loading…
3 of 5 tasks
Add --root-path to specificy HTTP prefix
#894 opened Jul 9, 2026 by alvarobartt Member • Draft
4 of 5 tasks
v1.9.4
1
1
feat(ort): allow overriding the ONNX filename via --onnx-filename
#891 opened Jul 1, 2026 by od28173 Loading… v1.9.4
5
Quality: Unbounded buffer allocation in PaddedBatch.from_pb
#890 opened Jun 27, 2026 by kumburovicbranko682-boop Loading…
5 tasks
1
feat(qwen3): support reranker on candle backend
#886 opened Jun 26, 2026 by malaiwah Loading…
4 of 5 tasks
1
1
feat: allow controlling startup warmup tokens
#884 opened Jun 25, 2026 by malaiwah Loading…
4 of 5 tasks
1
fix(candle): always apply attention masks for Qwen3 and Gemma3 batches
#883 opened Jun 24, 2026 by malaiwah Loading…
4 of 5 tasks
1
1
Add HTTP rerank endpoint coverage
#878 opened Jun 22, 2026 by jesco-absolut Loading…
1
support b300
#875 opened Jun 13, 2026 by deepindeed2022 Loading…
refactor: streamline tensor initialization and rearrange struct fields for clarity
#869 opened May 26, 2026 by Unmesh100 Loading…
1
chore: enable Dependabot weekly GitHub Actions bumps dependabot
#868 opened May 26, 2026 by hf-dependantbot-rollout Bot Loading…
Support modular Sentence Transformers cross-encoder rerankers (e.g. ettin-reranker)
#867 opened May 25, 2026 by hotchpotch Loading…
3 of 5 tasks
4
Upgrade hf-hub to 1.0.0-rc.1
#865 opened May 7, 2026 by assafvayner • Draft
2 of 4 tasks
feat: ROCm flash-attn varlen, triton layer norm, and AMD Dockerfile
#860 opened Apr 9, 2026 by Abdennacer-Badaoui Member Loading…
23
feat: better prometheus buckets for batch_size, isl, and input length
#847 opened Mar 20, 2026 by michaelfeil Contributor Loading…
5 tasks
v1.10.0
feat: add SM87 and SM110 compute capability support for Jetson devices
#844 opened Mar 12, 2026 by thomas-hiddenpeak Loading… v1.10.0
19
Refactor Dockerfile-cuda-all into compute-cap stages
#843 opened Mar 11, 2026 by alvarobartt Member • Draft
2 of 5 tasks
v1.10.0
1
Support Qwen3-Reranker
#835 opened Feb 20, 2026 by kozistr Contributor Loading…
4 of 5 tasks
v1.10.0
3
15
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.