Issues
- 0
Regarding warehouse updates and the forward-looking aspects in this regard.
#1671 opened by putizi-super - 0
Raspberry pi support?
#1670 opened by Vxtzq - 0
Add risc-v support
#1669 opened by zinovya - 0
pruned90_quant-none dataset download results in HTTP 403 Forbidden error
#1668 opened by daveisdigital - 3
[Question] About CPU performance
#1666 opened by mingfeima - 0
Updated Performance Against ONNXRuntime and OpenVINO
#1667 opened by vjsrinivas - 0
[QUESTION] Why model is taking so long to load?
#1665 opened by MariGaS - 2
- 3
Counting the object in the detection
#1661 opened by AJITKUMAR130012 - 1
onxx give the wrong inference
#1660 opened by AJITKUMAR130012 - 0
- 2
How can I make proper request to server
#1648 opened by Alex-SSK - 2
- 6
yolo-v8 in onnx-runtime outperforms deepsparse on iMX8
#1532 opened by Fritskee - 2
- 2
Unable to load DeepSparseSentenceTransformer
#1649 opened by Capt4in-Levi - 2
How can I use deepsparse instead of ultralytics
#1650 opened by piaoyaoi - 2
Unknown Pipeline task yolov8. Currently supported tasks are ['text_generation', 'opt', 'llama', 'code_gen', 'code_generation', 'codegen', 'image_classification', 'mpt']
#1651 opened by piaoyaoi - 3
YOLOv8 - Display bounding boxes and classes names in image using python.
#1641 opened by guiaugustoga987 - 2
[Question] about converting onnx model with dynamic batch size input to deepsparse model
#1647 opened by phamkhactu - 2
Using output_value as "token_embeddings" is broken for Sentence Transformer
#1448 opened by mikeybellissimo - 3
Paper: New algorithm for pruning
#1329 opened by gottlike - 1
Assertion at src/lib/core/topology.cpp:627
#1527 opened by Zorgosto - 3
- 1
- 5
Research: 4-bit quantization
#1369 opened by truenorth8 - 4
Purpose of exporter.export_onnx(sample_batch=torch.randn(1, 1, 28, 28))
#1632 opened by pradeepdev-1995 - 8
docker access denied error
#1452 opened by krrishdholakia - 5
Unsupported ONNX type 10 for FP16
#1501 opened by blizaga - 3
Python3.12?
#1629 opened by johnnynunez - 6
Segmentation fault (core dumped)
#1341 opened by Mahran-xo - 3
transformers_embedding-extraction for text-generation tasks
#1397 opened by BDHU - 5
NM: error: Node (/model/Add_1) Op (Add) [ShapeInferenceError] Incompatible dimension
#1430 opened by mneedham - 4
object detection on video with deepsparse
#1119 opened by aymeric75 - 1
Question on quantization size
#1429 opened by rajuptvs - 2
Assertion `!cache_sizes.empty()' failed
#1372 opened by akarym-sl - 1
Does he support stable diffusion or fooocus, or other image generation acceleration?
#1339 opened by libai-lab - 1
Adding Contributors Section to readme.md
#1361 opened by mohitd404 - 1
https://www.therapyinsightspractice.com
#1360 opened by Mjsmiles23 - 2
Support for Llama2?
#1322 opened by BDHU - 1
How to use Benchmark feature on custom dataset
#1256 opened by atultiwari - 16
- 7
- 2
DeepSparse uses 100% of the CPU.
#1193 opened by ik-ids - 11
Error when compiling YOLO-NAS model
#1170 opened by Y-T-G - 3
Support numpy > 1.21.6
#1093 opened by SmartAudioTools - 2
conflict error
#1105 opened by centurions - 2
Output is not the same as ONNX
#1092 opened by kopyl - 1
Please install deepsparse[yolo] to use this pathway
#1091 opened by kopyl - 4
Neural Magic: Encountered exception while trying to read arch.bin: Unable to determine instruction set
#1079 opened by aymeric75