GitHub / huggingface/text-embeddings-inference issues and pull requests
#608 - upgrade HPU FW to 1.21; upgrade transformers to 4.51.3
Pull Request -
State: open - Opened by kaixuanliu 2 months ago
#607 - upgrade pytorch and ipex to 2.7 version
Pull Request -
State: closed - Opened by kaixuanliu 3 months ago
- 2 comments
#606 - Fix the weight name in GTEClassificationHead
Pull Request -
State: closed - Opened by kozistr 3 months ago
- 1 comment
#605 - Wrong classification outputs with `WebOrganizer/FormatClassifier` model based on `gte-base-en-v1.5`
Issue -
State: closed - Opened by WissamAntoun 3 months ago
#604 - Gte diffs
Pull Request -
State: closed - Opened by Narsil 3 months ago
#603 - Update `text-embeddings-router --help` output
Pull Request -
State: closed - Opened by alvarobartt 3 months ago
- 1 comment
#602 - Remove duplicate short option '-p' to fix router executable
Pull Request -
State: closed - Opened by cebtenzzre 3 months ago
- 1 comment
#601 - Short option names must be unique for each argument, but '-p' is in use by both 'port' and 'prometheus_port'
Issue -
State: closed - Opened by cebtenzzre 3 months ago
#600 - distiluse-base-multilingual-cased-v2 error when start
Issue -
State: open - Opened by franklucky001 3 months ago
#599 - remove optimum-habana dependency
Pull Request -
State: closed - Opened by kaixuanliu 3 months ago
- 1 comment
#598 - Add integration tests for Gaudi
Pull Request -
State: open - Opened by baptistecolle 3 months ago
- 2 comments
#596 - Support NomicBert MoE
Pull Request -
State: closed - Opened by kozistr 3 months ago
- 7 comments
#595 - fix xpu env issue that cannot find right libur_loader.so.0
Pull Request -
State: closed - Opened by kaixuanliu 3 months ago
- 2 comments
#594 - enable flash mistral model for HPU device
Pull Request -
State: closed - Opened by kaixuanliu 3 months ago
- 4 comments
#593 - Fixing the CI (grpc path).
Pull Request -
State: closed - Opened by Narsil 3 months ago
#592 - Warmup padded models too.
Pull Request -
State: closed - Opened by Narsil 3 months ago
- 1 comment
#591 - Adding missing `head.` prefix in the weight name in `ModernBertClassificationHead`
Pull Request -
State: closed - Opened by kozistr 3 months ago
#590 - ModernBert Reranker not supported.
Issue -
State: closed - Opened by michaelfeil 3 months ago
- 2 comments
#589 - Add argument for configuring Prometheus port
Pull Request -
State: closed - Opened by kozistr 3 months ago
- 1 comment
#588 - Revert "Removing requirements file. (#585)"
Pull Request -
State: closed - Opened by Narsil 3 months ago
#587 - Moving to `uv` to enable dependency override and cleaner locks
Pull Request -
State: open - Opened by Narsil 3 months ago
- 1 comment
#586 - Bump `sccache` to 0.10.0 and `sccache-action` to 0.0.9
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
#585 - Removing requirements file.
Pull Request -
State: closed - Opened by Narsil 4 months ago
- 1 comment
#584 - Upgrade deps
Pull Request -
State: closed - Opened by Narsil 4 months ago
#583 - Removing candle-extensions to live on crates.io
Pull Request -
State: closed - Opened by Narsil 4 months ago
#582 - Add support for JinaAI Re-Rankers V1
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
- 1 comment
#581 - Add warmup client CLI option
Pull Request -
State: closed - Opened by vrdn-23 4 months ago
- 4 comments
#580 - CLI parameter to enable warm-up
Issue -
State: closed - Opened by vrdn-23 4 months ago
- 2 comments
#579 - Error: could not create backend -> jinaai/jina-reranker-v1-turbo-en
Issue -
State: closed - Opened by CoolFish88 4 months ago
- 10 comments
#578 - Fixup
Pull Request -
State: closed - Opened by Narsil 4 months ago
- 1 comment
#577 - Back with linting.
Pull Request -
State: closed - Opened by Narsil 4 months ago
- 1 comment
#576 - Fixing the tokenization routes token (offsets are in bytes, not in
Pull Request -
State: closed - Opened by Narsil 4 months ago
#575 - optimize the performance of FlashBert Path for HPU
Pull Request -
State: closed - Opened by kaixuanliu 4 months ago
- 2 comments
#574 - [Docs] Update quick tour
Pull Request -
State: closed - Opened by NielsRogge 4 months ago
- 1 comment
#573 - [Docs] Add cloud run example
Pull Request -
State: closed - Opened by NielsRogge 4 months ago
- 1 comment
#572 - Update `README.md` and `supported_models.md`
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
- 3 comments
Labels: documentation
#571 - TEI error for jinaai/jina-embeddings-v3 missing field `model_type` at line 51 column 1
Issue -
State: open - Opened by dromeuf 4 months ago
- 3 comments
#570 - Preparing for release 1.7.0 (candle update + modernbert).
Pull Request -
State: closed - Opened by Narsil 4 months ago
- 1 comment
#569 - Failing deployment on AWS Sagemaker endpoints
Issue -
State: closed - Opened by CoolFish88 4 months ago
- 10 comments
#568 - Update `docs/source/en/custom_container.md`
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
- 1 comment
#567 - Update the doc for submodule.
Pull Request -
State: closed - Opened by Narsil 4 months ago
#566 - Failed to build docker image due to missing cutlass/cutlass.h
Issue -
State: closed - Opened by CoolFish88 4 months ago
- 12 comments
#565 - Model Artifact Download Fails for cross-encoder/ms-marco-MiniLM-L6-v2 in TEI Docker (404 Errors)
Issue -
State: closed - Opened by arjungandeeva 4 months ago
- 2 comments
#564 - Fix `{Bert,DistilBert}SpladeHead` when loading from Safetensors
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
#563 - Is ipv6 supported?
Issue -
State: open - Opened by powerpistn 4 months ago
#562 - Enable ModernBert on metal
Pull Request -
State: closed - Opened by ivarflakstad 4 months ago
#561 - Update the `local attention mask` logic to work on MPS and CUDA in ModernBERT
Pull Request -
State: closed - Opened by kozistr 4 months ago
- 4 comments
#560 - Fixing FlashAttention ModernBert.
Pull Request -
State: closed - Opened by Narsil 4 months ago
- 1 comment
#559 - Use custom `serde` deserializer for JinaBERT models
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
- 1 comment
#558 - Fixing cudarc to the latest unified bindings.
Pull Request -
State: closed - Opened by Narsil 4 months ago
#557 - Short inputs cause /embed to randomly return empty vectors.
Issue -
State: open - Opened by superkelvint 4 months ago
- 5 comments
#556 - Sentence-Transformers-finetuned `jinaai/jina-embeddings-v2-small-en` doesn't work
Issue -
State: closed - Opened by deklanw 4 months ago
- 1 comment
#555 - Optimize the performance of FlashBert on HPU by using fast mode softmax
Pull Request -
State: closed - Opened by kaixuanliu 4 months ago
- 2 comments
#554 - Jina Reranker Models Not Supported in text-embeddings-inference
Issue -
State: closed - Opened by arjungandeeva 4 months ago
- 8 comments
#553 - can be model lazy load?
Issue -
State: closed - Opened by luzhongqiu 4 months ago
- 2 comments
#552 - Fix typos / formatting in CLI args in Markdown files
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
- 1 comment
#551 - Support for architecture: CodeXEmbedModel2B
Issue -
State: open - Opened by ForSeason 4 months ago
- 1 comment
#550 - add related docs for intel cpu/xpu/hpu container
Pull Request -
State: closed - Opened by kaixuanliu 4 months ago
- 3 comments
#549 - Fix linking bis
Pull Request -
State: closed - Opened by Narsil 4 months ago
#548 - cannot find tensor cls.predictions.decoder.weight
Issue -
State: closed - Opened by jetnet 4 months ago
#547 - Fixing the static-linking.
Pull Request -
State: closed - Opened by Narsil 4 months ago
#546 - Make `sliding_window` for `Qwen2` optional
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
- 3 comments
#545 - Upgrade candle3
Pull Request -
State: closed - Opened by Narsil 4 months ago
#544 - Error occurs when using ONNX model with text-embeddings-inference turing image
Issue -
State: open - Opened by gogomasaru 4 months ago
- 2 comments
#543 - Upgrade candle2
Pull Request -
State: closed - Opened by Narsil 4 months ago
#542 - Moving cublaslt into TEI extension for easier upgrade of candle globally
Pull Request -
State: closed - Opened by Narsil 4 months ago
#541 - Fix `FromAsCasing` warning in `Dockerfile-intel`
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
#540 - Prepare for release.
Pull Request -
State: closed - Opened by Narsil 4 months ago
- 5 comments
#539 - Fixing the impure flake devShell to be able to run python code.
Pull Request -
State: closed - Opened by Narsil 4 months ago
#538 - Fix `VarBuilder` handling in GTE e.g. `gte-multilingual-reranker-base`
Pull Request -
State: closed - Opened by Narsil 4 months ago
#537 - Small fixup.
Pull Request -
State: closed - Opened by Narsil 4 months ago
#536 - Feat support hf endpoint
Pull Request -
State: closed - Opened by Narsil 4 months ago
#535 - Use `--hf-token` instead of `--hf-api-token`
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
- 1 comment
#534 - Add `HF_HUB_USER_AGENT_ORIGIN`
Pull Request -
State: closed - Opened by alvarobartt 4 months ago
#533 - Could not start backend: cannot find tensor embeddings.word_embeddings.weight
Issue -
State: open - Opened by momomobinx 4 months ago
- 10 comments
#532 - Support for mixedbread-ai/mxbai-rerank-large-v2
Issue -
State: closed - Opened by jaehyeong-bespin 4 months ago
- 1 comment
#531 - Fixing the tests.
Pull Request -
State: closed - Opened by Narsil 4 months ago
- 1 comment
#530 - Fusing both Gte Configs.
Pull Request -
State: closed - Opened by Narsil 4 months ago
#529 - Fix typo on intel docker image
Pull Request -
State: closed - Opened by baptistecolle 4 months ago
#528 - error: could not compile `candle-core` (lib) due to 20 previous errors
Issue -
State: closed - Opened by tanliboy 4 months ago
- 4 comments
#527 - Relative URL without a base
Issue -
State: open - Opened by villagab4 4 months ago
- 3 comments
#526 - Refine model file download for python backend
Pull Request -
State: closed - Opened by kaixuanliu 4 months ago
- 8 comments
#525 - tokenize route got mismatch tokens
Issue -
State: closed - Opened by franklucky001 4 months ago
#524 - Support for jina-reranker-v2-base-multilingual
Issue -
State: open - Opened by icyxp 4 months ago
#523 - Support for Linq-AI-Research/Linq-Embed-Mistral
Issue -
State: open - Opened by thunder-007 4 months ago
- 3 comments
#522 - Build failed due to `half` and `rand` issue
Issue -
State: open - Opened by lytning98 4 months ago
- 3 comments
#521 - support image embedding inference
Issue -
State: open - Opened by lloydzhou 4 months ago
#520 - Prometheus metrics are empty
Issue -
State: closed - Opened by apage43 4 months ago
- 1 comment
#519 - feat: add support for "model_type": "gte"
Pull Request -
State: closed - Opened by anton-pt 4 months ago
- 1 comment
#518 - Add intel based images to the CI
Pull Request -
State: closed - Opened by baptistecolle 5 months ago
- 2 comments
#517 - add docker build for python backend in CI workflow
Pull Request -
State: closed - Opened by kaixuanliu 5 months ago
- 1 comment
#516 - dify,ragflow添加rerank模型失败
Issue -
State: closed - Opened by ljyong2010 5 months ago
#515 - make a WA in case Bert model do not have `safetensor` file
Pull Request -
State: closed - Opened by kaixuanliu 5 months ago
- 2 comments
#514 - Support for infly/inf-retriever-v1-1.5b
Issue -
State: closed - Opened by Hirro029 5 months ago
- 1 comment
#513 - fix bug for `MaskedLanguageModel` class`
Pull Request -
State: closed - Opened by kaixuanliu 5 months ago
- 4 comments
#512 - chore: Upgrade to tokenizers 0.21.0
Pull Request -
State: closed - Opened by lightsofapollo 5 months ago
#511 - Cannot load Qodo Embed 1 1.5b (upgrade to tokenizers 0.21.0)
Issue -
State: open - Opened by lightsofapollo 5 months ago
#510 - upgrade ipex to 2.6 version for cpu/xpu
Pull Request -
State: closed - Opened by kaixuanliu 5 months ago
- 5 comments
#509 - Optimize flash bert path for hpu device
Pull Request -
State: closed - Opened by kaixuanliu 5 months ago
- 5 comments
#508 - Update to latest candle version?
Issue -
State: closed - Opened by vrdn-23 5 months ago
- 2 comments