Skip to content

Pull requests: microsoft/onnxruntime-genai

New pull request New
35 Open 1,028 Closed
35 Open 1,028 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

[Model builder] Add support for Ernie 4.5 models
#1608 opened Jul 4, 2025 by xenova Loading…
Modify Model Builder to build paged attention models
#1605 opened Jul 3, 2025 by aciddelgado • Draft
Fix KV cache handling for TensorRT execution provider when in place kv is disable
#1604 opened Jul 3, 2025 by anujj • Draft
Add support for building a cuda + dml package
#1600 opened Jul 1, 2025 by baijumeswani Loading…
9
Correct model type as expected by genai CreateModel function for llm …
#1596 opened Jul 1, 2025 by anujj Loading…
4
Upload nightly python packages to nightly feed
#1593 opened Jun 29, 2025 by ajindal1 Loading…
7
transformers 4.52 support Gemma3 fix
#1583 opened Jun 25, 2025 by nenad1002 • Draft
Add SLM Engine support function calling
#1582 opened Jun 24, 2025 by kinfey Loading…
5
Support for Continuous Batching
#1580 opened Jun 23, 2025 by baijumeswani Loading…
Auto-generated baselines by 1ES Pipeline Templates
#1574 opened Jun 19, 2025 by microsoft-github-policy-service bot Loading…
[Builder] Ensure value creation order
#1555 opened Jun 13, 2025 by justinchuby Loading…
5
Add Encode with Options for add_special_tokens=True use-case
#1504 opened May 22, 2025 by sayanshaw24 Loading…
Update C and C# Chat Template Examples
#1494 opened May 19, 2025 by sayanshaw24 Loading…
[WIP]Stable Diffusion in GenAI
#1478 opened May 13, 2025 by selenayang888 • Draft
Postprocessing to share lm_head weights to embedding
#1461 opened May 8, 2025 by jiafatom Loading…
16
Model Builder: Add Post processing script to convert fp16/32 LM_HEAD to int8 and use tied embeddings
#1437 opened Apr 30, 2025 by sushraja-msft Loading…
build bitnet from HF bf16 model
#1421 opened Apr 24, 2025 by liqunfu Loading…
10
Add logging of ORT version and build info.
#1405 opened Apr 16, 2025 by edgchen1 Loading…
2
add extra_options use_channel_wised_quantization to builder.py
#1362 opened Mar 31, 2025 by bopeng1234 Loading…
2
re-enable debugging for dml
#1348 opened Mar 25, 2025 by aciddelgado Loading…
3
Add repetition test
#1339 opened Mar 21, 2025 by jiafatom Loading…
8
support audio model
#1286 opened Feb 27, 2025 by rui-ren Loading…
1
Fix Benchmark Script on DML EP
#1238 opened Feb 10, 2025 by aciddelgado Loading…
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
ProTip! Exclude everything labeled bug with -label:bug.