Skip to content

Pull requests: onnxruntime/mobius

New pull request New
24 Open 607 Closed
24 Open 607 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add experimental Qwen3.8 packed hybrid export for ORT GenAI Engine
#738 opened Sep 16, 2026 by Copilot AI • Draft
1
@titaiwangms
13
[TensorRT] Add TensorRT target and export qwen3-06b model
#736 opened Sep 15, 2026 by rui-ren Contributor Loading…
@titaiwangms @xiaoyu-work
6
Bump ruff from 0.16.2 to 0.16.6 in /requirements/lintrunner dependencies Pull requests that update a dependency file python Pull requests that update python code
#734 opened Sep 11, 2026 by dependabot Bot Loading…
2
Load quantized checkpoint weights per component
#733 opened Sep 8, 2026 by xiaoyu-work Member Loading…
@justinchuby
35
Add MatterGen crystal diffusion score-core export
#731 opened Sep 4, 2026 by justinchuby Member • Draft
22
Add TimesFM 3 multivariate forecasting support
#718 opened Sep 1, 2026 by justinchuby Member • Draft
8
Add GLM-5.3 Flash multimodal support automated
#713 opened Aug 31, 2026 by justinchuby Member Loading…
5
Export DeepSeek V4 ratio-4 compressed sparse attention
#700 opened Aug 29, 2026 by justinchuby Member • Draft
2
Make Qwen4Exp download diagnostics truthful
#698 opened Aug 28, 2026 by justinchuby Member • Draft
5
Enable direct GLM-5.2 GGUF tensor mapping
#682 opened Aug 27, 2026 by justinchuby Member Loading…
5
Tied quantized lm_head fix
#671 opened Aug 27, 2026 by neilmsft Loading…
@justinchuby
3
fix(deepseek-v4): per-layer CSA/HCA compressed-record symbolic dim
#622 opened Aug 25, 2026 by justinchuby Member • Draft
3
Add NVIDIA Nemotron 3.5 Lightning export support
#487 opened Aug 14, 2026 by justinchuby Member Loading…
19
Add WeatherNext-style ONNX conversion demo
#469 opened Aug 10, 2026 by Copilot AI • Draft
1
@justinchuby
9
Add composable world-model pipelines and Cosmos3 export
#466 opened Aug 8, 2026 by xiaoyu-work Member Loading…
@justinchuby
29
Fix gemma4 audio-encoder audio_features export rank (#570)
#444 opened Aug 1, 2026 by justinchuby Member Loading…
7
Add streaming multi-talker Parakeet RNN-T ASR model
#411 opened Jul 17, 2026 by themason2011 Contributor Loading…
4
chore(deps): Update lintrunner-adapters requirement from >=0.14.0 to >=0.14.1 in /requirements/lintrunner dependencies Pull requests that update a dependency file python Pull requests that update python code
#409 opened Jul 17, 2026 by dependabot Bot Loading…
2
Quantize Gemma4 per-layer embedding tables for WebGPU (INT4/INT8 configurable)
#403 opened Jul 14, 2026 by feich-ms Contributor • Draft
3 of 4 tasks
32
ort_genai: native processor configs for gemma-4-12B unified
#391 opened Jul 9, 2026 by justinchuby Member Loading…
8
Dashboard: collapse per-level status badges into a single highest-level badge
#347 opened Jun 9, 2026 by Copilot AI • Draft
1
@tadani3
6
Onboard Qwen2.5-Omni model
#193 opened Apr 23, 2026 by rui-ren Contributor Loading…
20
Add MaskedLMTask for protein/bio models (ESM-2, ProtBert) ai Created by an AI agent
#86 opened Apr 2, 2026 by justinchuby Member • Draft
@justinchuby
9
Add BitNet b1.58 ternary-weight model support ai Created by an AI agent
#83 opened Apr 2, 2026 by justinchuby Member • Draft
@justinchuby
8
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.