Skip to content

Issues: microsoft/onnxruntime-genai

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

26 Open 40 Closed
26 Open 40 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

phi-3-tutorial direct ML are not working properly
#476 opened May 20, 2024 by invent00
Feature Request: Specify seed in python SDK
#463 opened May 15, 2024 by Ben-Epstein
Model for llama-3-8B, EP: cpu, precision: int4 generated using onnxruntime-genai/src/python/py/models/builder.py has issues
#462 opened May 15, 2024 by jmopuri
3
Extend GeneratorParams.SetSearchOption to allow setting strings enhancement New feature or request
#454 opened May 14, 2024 by koepalex
GeneratorParams should not throw an exception enhancement New feature or request
#453 opened May 14, 2024 by skottmckay
1
Wasm/WebGPU backends? enhancement New feature or request
#452 opened May 14, 2024 by josephrocca
1
Regex decoding support enhancement New feature or request
#450 opened May 14, 2024 by sheepymeh
2
How to release GPU memory after each inference? enhancement New feature or request
#446 opened May 13, 2024 by nguyenthekhoig7
1
Is there a plan to support running Phi3 on the NPU of the Core Ultra enhancement New feature or request
#444 opened May 13, 2024 by goxia
Extensions for LLM
#442 opened May 11, 2024 by hannespreishuber
1
How to ignore EOS token when using onnxruntime-genai enhancement New feature or request
#436 opened May 10, 2024 by Tabrizian
Cannot use the DirectML packages to run on CPU in Windows App
#430 opened May 10, 2024 by natke
@PatriceVignola
5
Phi-3 does not load on iGPU vega 11 (Ryzen 2400g)
#403 opened May 4, 2024 by CodeI000I
@natke
1
Multi-target with .NET Standard 2.0 and .NET runtimes
#382 opened May 2, 2024 by michael-hawker
2
Querying the ids of all the DML devices and selecting a device for inference
#360 opened Apr 30, 2024 by jojo1899
@PatriceVignola
5
RTL support and other languages ?
#346 opened Apr 29, 2024 by PrestigeDevop
@natke
2
ImportError: libcudnn.so.8: cannot open shared object file: No such file or directory
#344 opened Apr 29, 2024 by xbotaria
@baijumeswani
6
Error while running Phi-3 with DML
#336 opened Apr 27, 2024 by tomas-pet
@PatriceVignola
8
Can't use this lib and the non-genai version of the onnxruntime in the same MSIX project.
#332 opened Apr 25, 2024 by azchohfi
5
Cannot run Genny sample with CUDA
#329 opened Apr 25, 2024 by strikene
@baijumeswani
3
cannot build phi2 model on system with 32 GB ram enhancement New feature or request
#319 opened Apr 24, 2024 by liqunfu
@kunal-vaishnavi
2
Phi-3 on mobile
#316 opened Apr 24, 2024 by cvb941
2
Phi-3 can't deal with Japanese. How can I solve this issue?
#314 opened Apr 24, 2024 by Hideki105
@wenbingl
12
Tokenizer throws an exception when created with Llama3
#281 opened Apr 22, 2024 by nmetulev
@wenbingl
2
Wheel file name does not get updated for new versions
#275 opened Apr 21, 2024 by natke
1
ProTip! Exclude everything labeled bug with -label:bug.