Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects, and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Developer articles
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
pytorch
executorch
Repository navigation
Code
Issues
901
(901)
Pull requests
521
(521)
Discussions
Actions
Projects
Wiki
Security and quality
Insights
More
items
All pull requests
Labels
135
(135)
Milestones
6
(6)
New pull request
Search pull requests
is
:
pr
state
:
open
is:pr state:open
Clear filter
Search
Pull requests
Open
521
(521)
Closed
22,044
(22,044)
Author
Label
Projects
Milestones
Reviews
Assignee
Sort by
Newest
descending
Sort…
Sort by Newest descending
More items
Comfortable display density
Compact display density
[MLX] Honor
descending
in sort/argsort lowering
release notes: none
#25419
·
doge-th
opened
Nov 21, 2026
·
·
1
4
[ExecuTorch][CUDA] Support multiple distinct Helion launches per program
CLA Signed
meta-exported
release notes: backends
#25418
·
Gasoonjia
opened
Nov 21, 2026
Contributor
·
·
3
Let KV-cache LLM exports take get_max_seq_len tokens per call
CLA Signed
release notes: llm
#25417
·
shoumikhin
opened
Nov 21, 2026
Contributor
·
·
2
Keep the threadpool when a new one cannot be created
CLA Signed
release notes: runtime
#25416
·
shoumikhin
opened
Nov 21, 2026
Contributor
·
·
2
Leave a method ready to run again after a kernel throws
CLA Signed
release notes: runtime
#25415
·
shoumikhin
opened
Nov 21, 2026
Contributor
·
·
2
Report truncated or missing data with the right error
CLA Signed
release notes: runtime
#25414
·
shoumikhin
opened
Nov 21, 2026
Contributor
·
·
2
Fix memory locking, close-on-exec and a bad free in the data loaders
CLA Signed
release notes: runtime
#25413
·
shoumikhin
opened
Nov 21, 2026
Contributor
·
·
2
Fix program lifetime and .ptd loading bugs in Module
CLA Signed
release notes: runtime
#25412
·
shoumikhin
opened
Nov 21, 2026
Contributor
·
·
2
[executorch][cuda] NVFP4: exact software E4M3 scale decode below SM89
CLA Signed
meta-exported
#25411
·
Gasoonjia
opened
Nov 21, 2026
Contributor
·
·
7
[MLX] Fuse native decode operators and save M5 measurements
CLA Signed
#25410
·
mergennachin
opened
Nov 21, 2026
Contributor
·
·
2
Retry transient Samsung device uploads in model tests
CLA Signed
#25409
·
psiddh
opened
Nov 21, 2026
Contributor
·
·
2
[executorch][muse] Draft CUDA DFlash from any singleton input token
CLA Signed
#25408
·
Gasoonjia
opened
Nov 21, 2026
Contributor
·
·
4
[Espressif] Lower fused-quant softmax with planned scratch
CLA Signed
#25406
·
rascani
opened
Nov 21, 2026
Contributor
·
20/20
·
·
2
[Espressif] Lower fused-quant spatial mean to ESP-NN
CLA Signed
#25405
·
rascani
opened
Nov 21, 2026
Contributor
·
19/20
·
·
2
Add opt-in W4A8 prefill GEMM for CudaCoalescedInt4Tensor on CUDA
CLA Signed
meta-exported
#25404
·
Gasoonjia
opened
Nov 21, 2026
Contributor
·
·
3
Qualcomm AI Engine Direct - Enable LPAI cut plan feature
CLA Signed
release notes: qualcomm
#25403
·
shewu-quic
opened
Nov 21, 2026
Contributor
·
·
2
Fuse Cortex-M convolution padding across explicit layout conversions
CLA Signed
#25401
·
rascani
opened
Nov 21, 2026
Contributor
·
4/4
·
·
6
Preserve quantized linear output dtype in Cortex-M passes
CLA Signed
#25400
·
rascani
opened
Nov 21, 2026
Contributor
·
3/4
·
·
6
Add FLUX.2 export and runtime support
CLA Signed
#25399
·
kiymetakdemir
opened
Nov 21, 2026
Contributor
·
·
2
Qualcomm AI Engine Direct - Support runtime custom-dequant convolution filters
release notes: qualcomm
#25396
·
quic-xiyushi
opened
Nov 20, 2026
Contributor
·
·
3
[ET-VK][conv2d] Prune padding taps in tiled conv2d
CLA Signed
meta-exported
#25391
·
SS-JIA
opened
Nov 20, 2026
Contributor
·
·
2
[executorch][cuda] Measure calls whose inputs start at a storage offset or share a storage
CLA Signed
meta-exported
#25390
·
Gasoonjia
opened
Nov 20, 2026
Contributor
·
·
2
[executorch][cuda] Benchmark many-row GEMMs and the cost of triton::linear's compile-time choice
CLA Signed
meta-exported
#25389
·
Gasoonjia
opened
Nov 20, 2026
Contributor
·
·
2
[executorch][cuda] Route strict FP32 GEMMs of 5 to 64 rows to triton::linear without measurement
CLA Signed
meta-exported
#25388
·
Gasoonjia
opened
Nov 20, 2026
Contributor
·
·
2
[executorch][cuda] Load triton::linear tiles as vectors from rows of any length that is a multiple of 4
CLA Signed
meta-exported
#25387
·
Gasoonjia
opened
Nov 20, 2026
Contributor
·
·
2
Previous
1
2
3
4
5
6
7
…
21
Next
You can’t perform that action at this time.