Skip to content

Pull requests: google-ai-edge/LiteRT-LM

New pull request New
114 Open 1,856 Closed
114 Open 1,856 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

Internal changes only.
#2123 opened Apr 29, 2026 by copybara-service Bot Loading…
Update CI-Win build environment and runner.
#2122 opened Apr 29, 2026 by copybara-service Bot Loading…
[litertlm] Fix lib name in Python API for Windows
#2121 opened Apr 29, 2026 by copybara-service Bot Loading…
Internal changes to FastVLM dataProcessor.
#2120 opened Apr 29, 2026 by copybara-service Bot Loading…
Workaround Metal memory leak by using HostMemory for text and audio state context.
#2118 opened Apr 29, 2026 by copybara-service Bot Loading…
Internal changes only.
#2117 opened Apr 29, 2026 by copybara-service Bot Loading…
Internal changes only.
#2116 opened Apr 29, 2026 by copybara-service Bot Loading…
Internal changes only.
#2113 opened Apr 29, 2026 by copybara-service Bot Loading…
Pack the LiteRT-LM Metadata using the flatbuffer-generated routines in litertln_header_schema_py_generated.py.
#2112 opened Apr 29, 2026 by copybara-service Bot Loading…
Call os.sendfile explicitly (shutil.copyfileobj does not do this) if it is available and we can get fileno()'s for the input/output files.
#2111 opened Apr 29, 2026 by copybara-service Bot Loading…
Rename serve_integration_test to serve_gemini_integration_test.
#2109 opened Apr 29, 2026 by copybara-service Bot Loading…
[WIP] Add linear attention cache type support
#2106 opened Apr 28, 2026 by copybara-service Bot Loading…
internal code change.
#2104 opened Apr 28, 2026 by copybara-service Bot Loading…
Add test utility to overwrite UUID in LiteRT-LM files
#2103 opened Apr 28, 2026 by copybara-service Bot Loading…
[litertlm] Make GPU enum works for all types of GPU models
#2100 opened Apr 28, 2026 by copybara-service Bot Loading…
Improve cancellation handling and resource release in threaded executor.
#2099 opened Apr 28, 2026 by copybara-service Bot Loading…
internal code change.
#2098 opened Apr 28, 2026 by copybara-service Bot Loading…
Internal change
#2091 opened Apr 28, 2026 by copybara-service Bot Loading…
[litertlm] auto-select engine type based on backend in C / Python
#2087 opened Apr 27, 2026 by copybara-service Bot Loading…
Add a litertlm_utils that contains helper functions for reading/writing LiteRT-LM files.
#2083 opened Apr 27, 2026 by copybara-service Bot Loading…
Honor session-level sampler params (seed/temperature/topK/topP) on GPU and NPU executors
#2081 opened Apr 27, 2026 by DenisovAV Loading…
1
memory_mapped_file_posix: map weights as PROT_READ to avoid iOS VM commit
#2076 opened Apr 26, 2026 by JMMeow Loading…
2 of 3 tasks
Internal changes ....
#2068 opened Apr 24, 2026 by copybara-service Bot Loading…
Internal changes only.
#2061 opened Apr 24, 2026 by copybara-service Bot Loading…
Update dependencies of litert_lm
#2054 opened Apr 23, 2026 by copybara-service Bot Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.