issues
search
michaelfeil
/
infinity
Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip
https://michaelfeil.github.io/infinity/
MIT License
1.31k
stars
96
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Allow enabling rerankers raw_scores
#393
rawsh
closed
3 hours ago
1
Support data:image syntax for embeddings_image api
#391
stikkireddy
closed
2 days ago
1
Follow up PR for Audio End to End testing
#390
wirthual
closed
2 days ago
3
support Alibaba-NLP/gte-Qwen2-1.5B-instruct
#388
yinggoga
closed
3 days ago
2
WIP: End to End test for vision and audio
#386
wirthual
closed
4 days ago
2
Feature: Add Support for Data URI
#385
davleop
closed
1 day ago
6
Different results between sentence-transformers and infinity server
#384
stikkireddy
closed
1 week ago
2
Make infinity rerank more compatible with jina
#383
shizidushu
closed
6 days ago
7
add client packages
#382
michaelfeil
closed
1 week ago
1
add libsound for docker arm build
#381
michaelfeil
closed
1 week ago
1
Update README. Extract audio related code into own utils
#380
wirthual
closed
1 week ago
1
extract audio code in audio utils. Update README
#379
wirthual
closed
1 week ago
2
Add a End-to-end unit test for image embeddings and audio embeddings
#378
michaelfeil
opened
1 week ago
2
Audio: OpenAI API
#377
michaelfeil
closed
1 week ago
1
async requests enabled
#376
michaelfeil
closed
1 week ago
1
verify sampling rate of audio input to audio model
#375
michaelfeil
closed
1 week ago
0
add verification check for audio sampling rate and image size
#374
michaelfeil
closed
1 week ago
1
add weakref to sync engine
#373
michaelfeil
closed
1 week ago
1
when use engine optimum device tensorrt,startup fail
#372
weibingo
opened
1 week ago
5
prepend v1 to OpenAI compatible APIs
#371
samos123
opened
1 week ago
3
Memory allocation error with Alibaba-NLP/gte-multilingual-reranker-base
#370
John42506176Linux
opened
1 week ago
5
Update README.md
#368
shell-nlp
closed
1 week ago
2
Subsequent requests hang if one failed for embeddings_image api
#367
kimson99
closed
1 week ago
1
How to change the service's batch-size
#366
TOMATODA
closed
1 week ago
1
format with ruff
#365
michaelfeil
closed
2 weeks ago
1
WIP: Add CLAP support
#364
wirthual
closed
1 week ago
7
Reranker dynamic quantization
#363
rawsh-rubrik
opened
2 weeks ago
1
jinaai/jina-reranker-v1-*-en does not work with optimum
#362
rawsh
opened
2 weeks ago
0
Issue running cross-encoder onnx model exported with optimum-cli
#361
rawsh
opened
2 weeks ago
2
Write a custom flash-attention function for the deberta model.
#359
wolfassi123
opened
2 weeks ago
1
Device = None
#358
wolfassi123
closed
2 weeks ago
1
Add mount path support
#356
taoari
closed
3 weeks ago
1
Question: Support for colbertv2.0 ?
#355
shatealaboxiaowang
opened
3 weeks ago
1
minicpm3-embedding and minicpm3-reranker
#354
lyj157175
closed
1 week ago
4
Solution to #258 [CLIP][Server/Engine] Send images to engine / accept PIL images
#353
Gavinfornever
closed
2 weeks ago
7
Support Integration with KServe
#352
indranilr
opened
3 weeks ago
1
Update README.md
#351
michaelfeil
closed
1 month ago
1
base64 encoding option for embeddings
#350
michaelfeil
closed
4 weeks ago
1
Support `encoding_format` from the official OpenAI-API for compatibility
#349
Matti-Koopa
closed
4 weeks ago
8
add disk_cleanup action
#348
kartik-ganesh
closed
1 month ago
2
fixing link
#347
aowen14
closed
1 month ago
1
Update README.md with logos
#346
michaelfeil
closed
1 month ago
1
embeddings_image not work with model-id sentence-transformers/clip-ViT-B-32-multilingual-v1
#345
xyxu
closed
1 month ago
2
add support for deberta
#344
Stealthwriter
closed
1 month ago
2
add vast example to infra
#343
aowen14
closed
1 month ago
1
Reranker API “top_k” Support
#342
etwk
opened
1 month ago
4
Embedding High VRAM Usage
#341
etwk
closed
1 month ago
4
BGE-m3 (dense + sparse) support
#340
Hokyjack
closed
1 month ago
2
update docs, bump version
#339
michaelfeil
closed
1 month ago
0
List should have at most 2048 items after validation: Context Length Error
#338
TimilsinaBimal
closed
1 month ago
1
Next