Skip to content

Pull requests: google-ai-edge/LiteRT

New pull request New
746 Open 3,352 Closed
746 Open 3,352 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

Update interpreter and subgraph to provide external buffer id and tensor mapping
#4340 opened Oct 31, 2025 by copybara-service bot Loading…
Internal LiteRT change.
#4339 opened Oct 31, 2025 by copybara-service bot Loading…
Internal LiteRT change.
#4338 opened Oct 31, 2025 by copybara-service bot Loading…
Add Op index in IR for internal debugging.
#4337 opened Oct 31, 2025 by copybara-service bot Loading…
Improve eval script, also check if device has been alive for long enough.
#4336 opened Oct 31, 2025 by copybara-service bot Loading…
Enable examples plugin on Windows
#4333 opened Oct 31, 2025 by fujunwei Loading…
1
Unconditionally include YNNPACK
#4329 opened Oct 31, 2025 by copybara-service bot Loading…
Misc tweaks ats.
#4324 opened Oct 30, 2025 by copybara-service bot Loading…
Add no push option for device scripting
#4323 opened Oct 30, 2025 by copybara-service bot Loading…
Prepare compiler partition option and add flag parse/unparse helper for tooling usage.
#4322 opened Oct 30, 2025 by copybara-service bot Loading…
Set qnn flags for ats.
#4321 opened Oct 30, 2025 by copybara-service bot Loading…
Switch ats to use micro seconds for latency instead of nano
#4320 opened Oct 30, 2025 by copybara-service bot Loading…
Allow repeatable flags for test filtering in ats for convenience.
#4319 opened Oct 30, 2025 by copybara-service bot Loading…
Use Sin for fp data in ats. Get rid of the flag for now, just use defaults.
#4317 opened Oct 30, 2025 by copybara-service bot Loading…
Use buffer size for dynamic output tensors.
#4316 opened Oct 30, 2025 by copybara-service bot Loading…
PR #4227: Qualcomm AI Engine Direct - Optimize memory footprint and init time.
#4314 opened Oct 30, 2025 by copybara-service bot Loading…
Internal changes only.
#4313 opened Oct 30, 2025 by copybara-service bot Loading…
Update litert lm runtime/components/preprocessor to stop using c enum
#4312 opened Oct 30, 2025 by copybara-service bot Loading…
Update litert lm runtime/components to stop using c enum
#4311 opened Oct 30, 2025 by copybara-service bot Loading…
Update litert lm runtime components to stop using c api
#4310 opened Oct 30, 2025 by copybara-service bot Loading…
Update litert lm runtime executor and util to stop using c enum
#4309 opened Oct 30, 2025 by copybara-service bot Loading…
Update litert lm embedding to stop using c enum
#4308 opened Oct 30, 2025 by copybara-service bot Loading…
Detect potential race conditions in the XNNPack weight cache provider usage.
#4304 opened Oct 30, 2025 by copybara-service bot Loading…
Add a function to stop building a weight cache.
#4303 opened Oct 30, 2025 by copybara-service bot Loading…
Loosen the restrictions in MMapWeightCacheProvider::OffsetToAddr.
#4302 opened Oct 30, 2025 by copybara-service bot Loading…
ProTip! no:milestone will show everything without a milestone.