Skip to content

Pull requests: microsoft/onnxruntime-genai

New pull request New
25 Open 779 Closed
25 Open 779 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Whisper Redesigned Solution
#1229 opened Feb 5, 2025 by kunal-vaishnavi Loading…
4 tasks
Continuous Decoding for C/C++ Examples 0.6.0
#1224 opened Feb 4, 2025 by ajindal1 Loading…
Overlap KV cache update for WindowedKeyValueCache in DecoderOnlyPipelineState
#1222 opened Feb 4, 2025 by edgchen1 Loading…
4
Add DML tests
#1219 opened Feb 3, 2025 by aciddelgado Loading…
1
Create DeepSeek-R1-Tutorial.md
#1215 opened Feb 1, 2025 by parinitarahi Loading…
15
[WIP] Quark Quantizer Support
#1207 opened Jan 29, 2025 by shobrienDMA Loading…
fix bug in python benchmark script
#1206 opened Jan 29, 2025 by thevishalagarwal Loading…
Move SetInputs to Generator
#1205 opened Jan 28, 2025 by aciddelgado • Draft
Adding hidden_states to generator state to enable embedding scenarios
#1203 opened Jan 24, 2025 by vortex-captain Loading…
1
Refactor providers into separate libraries
#1190 opened Jan 16, 2025 by RyanUnderhill Loading…
42
[Model builder] Add option to exclude cache in inputs and outputs
#1162 opened Dec 22, 2024 by xenova Loading…
10
Avoid potential desynchronization of cpu and device memory
#1132 opened Dec 9, 2024 by aciddelgado Loading…
1
Add Debug Pipelines
#1116 opened Dec 3, 2024 by aciddelgado Loading…
3
Added config files for Doxygen
#1107 opened Nov 29, 2024 by skyline75489 • Draft
4
Make tests discoverable at build time
#1094 opened Nov 22, 2024 by baijumeswani Loading…
Allow OgaShutdown to be called multiple times
#1080 opened Nov 20, 2024 by RyanUnderhill Loading…
2
Add Quantized_model + float LoRA model scenario to model builder
#1043 opened Nov 7, 2024 by apsonawane Loading…
26
Support constrained decoding
#1038 opened Nov 6, 2024 by Taka152 Loading…
36
Add an IChatClient implementation to OnnxRuntimeGenAI
#987 opened Oct 16, 2024 by stephentoub Loading…
18
Make Microsoft.ML.OnnxRuntimeGenAI.Tokenizer a Microsoft.ML.Tokenizers.Tokenizer
#970 opened Oct 11, 2024 by stephentoub Loading…
2
Add llama C++ example
#926 opened Sep 25, 2024 by natke Loading…
10
Introducing Genny MAUI
#870 opened Sep 4, 2024 by skyline75489 • Draft
Calng-format
#680 opened Jul 5, 2024 by yuslepukhin • Draft
[WIP] standalone shared library for custom op using ORTX-extensions infrastructure
#433 opened May 10, 2024 by jslhcl • Draft
add docs for using phi models directly
#407 opened May 6, 2024 by Ben-Epstein Loading…
1
ProTip! Follow long discussions with comments:>50.