Skip to content

Issues: microsoft/onnxruntime-genai

Beta
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
105 Open 311 Closed
105 Open 311 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
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
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[DML] [iGPU] [AMD] [Intel] GPU command exception ep:DML model:transformer
#667 opened Jul 2, 2024 by tjtanaa
6
Device API throws exception bug Something isn't working ep:DML
#488 opened May 21, 2024 by natke
@PatriceVignola
8
With Latest GeForce Driver v555 - Microsoft.ML.OnnxRuntimeGenAI.OnnxRuntimeGenAIException: The GPU will not respond to more commands, most likely because of an invalid command passed by the calling application. ep:DML
#501 opened May 22, 2024 by AshD
@PatriceVignola
13
ONNXRuntime-genai doesn't release GPU memory after first inference ep:CUDA performance
#526 opened May 28, 2024 by Positronx
@baijumeswani
2
Phi-3-mini-4k-instruct-onnx model generates nonsensical results when prompt is longer than half of the context window length bug Something isn't working
#552 opened May 31, 2024 by jackylu0124
@baijumeswani
12
[.NET] Genny chat-bot sample doesn't support DirectML and Phi-3 ep:DML
#569 opened Jun 5, 2024 by asmirnov82
1
@PatriceVignola
10
Phi-3-Mini fails to execute on long prompts on Intel integrated GPU with DirectML ep:DML
#570 opened Jun 5, 2024 by ofirzaf
@PatriceVignola
13
Memory leak during back-to-back inferences ep:DML model:transformer performance
#590 opened Jun 10, 2024 by jeremyfowers
@PatriceVignola
20
is there any exmaple of phi-3 vision model deploy on Android? platform:mobile
#608 opened Jun 14, 2024 by henrywang0314
9
GPU suspended (887A0005) while running example in DML ep:DML
#628 opened Jun 21, 2024 by skyline75489
@PatriceVignola
7
More API parameters could be const
#631 opened Jun 21, 2024 by skottmckay
1
Performance Regression in DML ep:DML performance
#641 opened Jun 25, 2024 by contentis
@PatriceVignola
3
Querying the ids of all the DML devices and selecting a device for inference ep:DML
#360 opened Apr 30, 2024 by jojo1899
@PatriceVignola
8
GPU driver error when using AMD eGPU via DirectML ep:DML model:transformer platform:windows
#644 opened Jun 25, 2024 by x0wllaar
2
Nodes are not topologically sorted from models generated by model builder
#707 opened Jul 17, 2024 by BowenBao
@kunal-vaishnavi
3
Inference with batching is significantly slower than without batching. ep:CUDA
#714 opened Jul 20, 2024 by Jester6136
2
[DML] Test that destroys a generator, tweaks GeneratorParams and then creates another generator throws a KV_Cache exception ep:DML platform:windows
#722 opened Jul 24, 2024 by yuslepukhin
Issues running on Ryzen ep:DML platform:windows waiting-for-customer
#728 opened Jul 26, 2024 by jarroddavis68
@PatriceVignola
5
Setting specific device_id with set_current_gpu_device_id not working bug Something isn't working ep:CUDA
#730 opened Jul 29, 2024 by MadMenHitBooker
2
Back-to-back inferences speed slowdown over time bug Something isn't working ep:DML model:transformer performance
#737 opened Jul 31, 2024 by xcmgttacct
10
Builder '-m' does not support quantized models
#771 opened Aug 8, 2024 by BowenBao
2
Nightly builds packaging
#772 opened Aug 9, 2024 by jarroddavis68
@baijumeswani
6
How to modify the dtype of inputs?
#795 opened Aug 14, 2024 by trajepl
@baijumeswani
CodeQwen running error model:transformer
#805 opened Aug 16, 2024 by aspi632
3
Compiling ort_genai_c.h as a C file fails due to <cstddef> inclusion
#1512 opened May 28, 2025 by nizarbenalla
2
ProTip! Updated in the last three days: updated:>2025-05-25.