michaelfeil/infinity issues and pull requests

#532 - gme-Qwen2-VL-2B-Instruct

Issue - State: open - Opened by rawsh-rubrik 6 days ago - 1 comment

#531 - Low throughput with modernbert

Issue - State: open - Opened by rawsh-rubrik 8 days ago - 3 comments

#530 - Changes by create-pull-request action

Pull Request - State: open - Opened by github-actions[bot] 8 days ago

#529 - Add permission for opening PR of auto generated client code

Issue - State: closed - Opened by wirthual 8 days ago - 2 comments

#528 - README: add example for using local model wtth docker container

Pull Request - State: closed - Opened by wirthual 9 days ago - 1 comment

#526 - add vision client template

Pull Request - State: closed - Opened by wirthual 16 days ago - 1 comment

#525 - update torch

Pull Request - State: open - Opened by michaelfeil 20 days ago - 1 comment

#524 - Version check step

Pull Request - State: closed - Opened by wirthual 20 days ago - 4 comments

#523 - add new st version

Pull Request - State: closed - Opened by michaelfeil 21 days ago - 1 comment

#522 - bump client version

Pull Request - State: closed - Opened by wirthual 21 days ago - 1 comment

#521 - Deployment: infifnity_client version does not match with infinity_emb version

Issue - State: closed - Opened by wirthual 21 days ago

#520 - 0.0.75 release

Pull Request - State: closed - Opened by michaelfeil 28 days ago - 1 comment

#519 - matryoshka_dim=512 is not in a valid range. Select between 1 and 128.

Issue - State: open - Opened by antonmark 29 days ago - 2 comments

#518 - inference speed

Issue - State: open - Opened by fst813 about 1 month ago - 1 comment

#517 - Infinity embed crashes too easily

Issue - State: open - Opened by taoari about 1 month ago

#517 - Infinity embed crashes too easily

Issue - State: open - Opened by taoari about 1 month ago - 6 comments

#516 - Update verbose parameter when initializing ModelWorker

Pull Request - State: closed - Opened by aRyBernAlTEglOTRO about 1 month ago - 1 comment

#515 - [BUG} Typo for vervose

Issue - State: closed - Opened by aRyBernAlTEglOTRO about 1 month ago - 2 comments

#514 - GPU Memory is not freed after embedding operations

Issue - State: open - Opened by Aelentel about 1 month ago - 3 comments

#512 - Implement Colbert for Optimum

Issue - State: open - Opened by wwymak about 1 month ago

#511 - Question: Different embedding output of colbert style models when using torch vs optimum engines -- is this the expected behaviour?

Issue - State: closed - Opened by wwymak about 1 month ago - 1 comment

#510 - Set default `CMD` to `v2` in Dockerfiles if no command is set

Issue - State: open - Opened by stevapple about 1 month ago - 1 comment

#509 - add better bettertransformers support

Pull Request - State: closed - Opened by michaelfeil about 2 months ago - 1 comment

#508 - Modernbert install from git

Pull Request - State: closed - Opened by michaelfeil about 2 months ago - 1 comment

#507 - ColQwen on RunPOD. ValueError: The checkpoint you are trying to load has model type `paligemma` but Transformers does not recognize this architecture.

Issue - State: open - Opened by simjak about 2 months ago

#507 - ColQwen on RunPOD. ValueError: The checkpoint you are trying to load has model type `paligemma` but Transformers does not recognize this architecture.

Issue - State: open - Opened by simjak about 2 months ago - 1 comment

#505 - Separating infinity server capability from reranking capability

Issue - State: closed - Opened by noamgershi about 2 months ago - 1 comment

#504 - ModernBERT

Issue - State: closed - Opened by qdrddr about 2 months ago - 3 comments

#503 - Support for colbert style late interaction models in rerank endpoint

Issue - State: open - Opened by wwymak about 2 months ago

#502 - Compatible with Deberta series models

Issue - State: closed - Opened by shell-nlp 2 months ago

#502 - Compatible with Deberta series models

Issue - State: closed - Opened by shell-nlp 2 months ago

#501 - move cli to extra file, macOS tests add documentation

Pull Request - State: closed - Opened by michaelfeil 2 months ago - 1 comment

#500 - Reranker detected as embedder Jina rerank tiny

Issue - State: open - Opened by rawsh-rubrik 2 months ago - 3 comments

#499 - Add support for nomic-embed-vision-v1.5

Issue - State: closed - Opened by hekmon 2 months ago - 3 comments

#498 - torch.OutOfMemoryError: CUDA out of memory. when serving NV-Embed-V2 on 8 40G A100 GPUs

Issue - State: closed - Opened by atanikan 2 months ago - 6 comments

#497 - Support for models trained with SetFit for classification

Issue - State: open - Opened by S1LV3RJ1NX 2 months ago - 1 comment

#496 - Why not support api_key argument?

Issue - State: closed - Opened by BarrySmith 2 months ago - 3 comments

#495 - What are the main differences between using this repo and BentoInfinity?

Issue - State: closed - Opened by noamgershi 2 months ago - 3 comments

#494 - new-release?

Pull Request - State: closed - Opened by michaelfeil 2 months ago - 1 comment

#493 - BetterTransformer is not available for model fine-tuned on GTE-base

Issue - State: closed - Opened by Tejaswgupta 2 months ago - 2 comments

#492 - Adding optimum option for PredictEngine

Pull Request - State: closed - Opened by wwymak 2 months ago - 3 comments

#492 - Adding optimum option for PredictEngine

Pull Request - State: open - Opened by wwymak 2 months ago - 2 comments

#492 - Adding optimum option for PredictEngine

Pull Request - State: open - Opened by wwymak 2 months ago - 2 comments

#491 - Runtime Error with Alibaba-NLP/gte-multilingual-reranker-base with docker

Issue - State: closed - Opened by uabbas 2 months ago - 4 comments

#491 - Runtime Error with Alibaba-NLP/gte-multilingual-reranker-base with docker

Issue - State: closed - Opened by uabbas 2 months ago - 3 comments

#491 - Runtime Error with Alibaba-NLP/gte-multilingual-reranker-base with docker

Issue - State: closed - Opened by uabbas 2 months ago - 3 comments

#490 - Support for matryoshka embeddings

Pull Request - State: closed - Opened by wirthual 3 months ago - 7 comments

#490 - Support for matryoshka embeddings

Pull Request - State: open - Opened by wirthual 3 months ago - 2 comments

#490 - Support for matryoshka embeddings

Pull Request - State: open - Opened by wirthual 3 months ago - 2 comments

#489 - add max size

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#488 - Optimum/Onnx support in PredictEngine

Issue - State: closed - Opened by wwymak 3 months ago - 1 comment

#487 - Fix python classification example

Pull Request - State: closed - Opened by molntamas 3 months ago - 2 comments

#486 - Adds neuron support

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#484 - Binary quantization - evaluate quality

Issue - State: open - Opened by cduk 3 months ago - 1 comment

#483 - health endpoint does not really provide insights about healthiness

Issue - State: open - Opened by bufferoverflow 3 months ago - 3 comments

#483 - health endpoint does not really provide insights about healthiness

Issue - State: open - Opened by bufferoverflow 3 months ago - 3 comments

#483 - health endpoint does not really provide insights about healthiness

Issue - State: open - Opened by bufferoverflow 3 months ago - 3 comments

#482 - Pass kwargs to encoder

Issue - State: open - Opened by RichaMax 3 months ago - 2 comments

#482 - Pass kwargs to encoder

Issue - State: open - Opened by RichaMax 3 months ago - 4 comments

#481 - Dtype changes

Pull Request - State: closed - Opened by bavithra-devi 3 months ago - 1 comment

#479 - Use different revision for more one model.

Issue - State: closed - Opened by rohilrg-diabolocom 3 months ago - 5 comments

#477 - v2 cli does not support loading models from local directory

Issue - State: closed - Opened by bufferoverflow 3 months ago - 11 comments

#476 - support for dimensions field like in OpenAI text-embedding-3, thanks

Issue - State: closed - Opened by ericg108 3 months ago - 8 comments
Labels: help wanted, good first issue

#475 - Fix: openvino

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#474 - Support for custom SentenceTransformer models

Issue - State: open - Opened by wwymak 3 months ago - 3 comments

#473 - Token count endpoint

Issue - State: closed - Opened by Haakooto 3 months ago - 2 comments

#472 - Add API for Image Embeddings Using ColPali/ColQwen

Issue - State: closed - Opened by kiendn1 3 months ago - 1 comment

#471 - update transformers package

Pull Request - State: closed - Opened by wirthual 3 months ago - 6 comments

#470 - NV-Embed-v2: AttributeError: 'LatentAttentionConfig' object has no attribute '_attn_implementation_internal'

Issue - State: closed - Opened by wirthual 3 months ago - 2 comments

#469 - update release pipeline

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#468 - refactor -> select_model(functional)

Pull Request - State: open - Opened by michaelfeil 3 months ago - 1 comment

#467 - optimum openvino

Pull Request - State: open - Opened by michaelfeil 3 months ago - 1 comment

#466 - Revert "Update functional.py"

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#465 - Refactor pydantic 2

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#464 - Optimum amd support

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#463 - dunzhang/stella_en_400M_v5 - xformers - requires device with capability > (8, 0) but your GPU has capability (7, 5) (too old)

Issue - State: closed - Opened by HighSec-org 3 months ago - 9 comments

#462 - Queue refactor

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#458 - bump version for embed

Pull Request - State: open - Opened by michaelfeil 3 months ago - 1 comment

#457 - Revert "Update release_docker_container.yaml"

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#456 - Colbert

Pull Request - State: closed - Opened by michaelfeil 3 months ago - 1 comment

#455 - Do we support late interaction models like ColBERT? Or Sparse models like BM25?

Issue - State: open - Opened by S1LV3RJ1NX 3 months ago

#454 - [Feature] [Optimum] [Intel] [OpenVINO] Add OpenVINO backend support through Optimum-Intel

Pull Request - State: open - Opened by tjtanaa 3 months ago - 1 comment

#453 - README: Add KubeAI under integrations

Pull Request - State: closed - Opened by samos123 4 months ago - 2 comments

#452 - Model: Device-id and data-parallel inference in CLI and Torch

Pull Request - State: closed - Opened by michaelfeil 4 months ago - 1 comment

#451 - Support for Model2Vec Embedding models

Issue - State: closed - Opened by S1LV3RJ1NX 4 months ago - 13 comments

#450 - OpenAIEmbeddings is flattening out the embeddings received from colpali models.

Issue - State: closed - Opened by S1LV3RJ1NX 4 months ago - 7 comments

#449 - MiniCPM-Embedding support

Issue - State: closed - Opened by gaohongkui 4 months ago - 4 comments

#448 - Why does the EMB performance drop when the dabatch is requested?

Issue - State: open - Opened by sunzx8 4 months ago - 2 comments

#446 - Fixed Broken License Link in README

Pull Request - State: closed - Opened by niranjan-kurhade 4 months ago

#445 - License Link Broken in Readme

Issue - State: closed - Opened by niranjan-kurhade 4 months ago

#444 - change embedding response object to list for openai compatibility

Pull Request - State: closed - Opened by wirthual 4 months ago - 2 comments

#443 - [AMD] [ROCm] [Optimum] Add optimum-amd support

Pull Request - State: closed - Opened by tjtanaa 4 months ago - 7 comments

#442 - Update release_docker_container.yaml

Pull Request - State: closed - Opened by AranavMahalpure 4 months ago - 2 comments

#441 - Add PR template (With changes)

Pull Request - State: closed - Opened by fadkeabhi 4 months ago - 1 comment

#440 - updates README

Pull Request - State: closed - Opened by HimangshuYadav 4 months ago - 1 comment

GitHub / michaelfeil/infinity issues and pull requests