Skip to content

Pull requests: google-ai-edge/ai-edge-quantizer

New pull request New
42 Open 433 Closed
42 Open 433 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

Refactor: Initialize Calibrator in individual tests.
#486 opened Apr 29, 2026 by copybara-service Bot Loading…
Add a litertlm_utils that contains helper functions for reading/writing LiteRT-LM files.
#485 opened Apr 29, 2026 by copybara-service Bot Loading…
Use the magic header bytes defined in litertlm_core.
#484 opened Apr 29, 2026 by copybara-service Bot Loading…
Change the OpQuantizationRecipe's operation: TFLOperationName field to operators: set[TFLOperationName].
#483 opened Apr 28, 2026 by copybara-service Bot Loading…
fix: handle N-D tensors in large-tensor CHANNELWISE quantization
#482 opened Apr 28, 2026 by QuadraKev Loading…
1
1
Export the LiteRT-LM file header magic bytes in litertlm_core.py for consistency.
#481 opened Apr 27, 2026 by copybara-service Bot Loading…
Move quantization recipe name/file resolution to recipe_utils.py.
#480 opened Apr 27, 2026 by copybara-service Bot Loading…
Set required-environments to the current underlying architecture for each test.
#473 opened Apr 20, 2026 by copybara-service Bot Loading…
Internal change only.
#462 opened Mar 25, 2026 by copybara-service Bot Loading…
Replicate the scalar scaling factor for 4-bit tensor-wise quantized weights to the number of channels, as is done for 8-bit weights.
#455 opened Mar 18, 2026 by copybara-service Bot Loading…
Add SPACE_TO_DEPTH support for STATIC_WI8_AI16 quantization CLA:yes
#445 opened Mar 14, 2026 by nj-1015 Loading…
3 tasks done
1
Generate Per-Op report with the progress report.
#439 opened Mar 9, 2026 by copybara-service Bot Loading…
Add a function update_packed_buffer that modifies the offset and size values of a packed Buffer object in-place.
#438 opened Mar 9, 2026 by copybara-service Bot Loading…
Add Kokoro configurations for automated ai-edge-quantizer releases.
#437 opened Mar 5, 2026 by copybara-service Bot Loading…
Enable A16W8 quantization options and update scripts.
#436 opened Mar 5, 2026 by copybara-service Bot Loading…
Add script for inference comparison and make prompt formatting optional.
#435 opened Mar 5, 2026 by copybara-service Bot Loading…
Add script and tool to merge calibration results.
#434 opened Mar 5, 2026 by copybara-service Bot Loading…
Add calibration scripts and XManager launcher for NanoV4 models.
#433 opened Mar 5, 2026 by copybara-service Bot Loading…
This is an internal change
#430 opened Mar 5, 2026 by copybara-service Bot Loading…
Ignore, caused by diffbase
#429 opened Mar 5, 2026 by copybara-service Bot Loading…
Ignore, caused by diffbase
#428 opened Mar 5, 2026 by copybara-service Bot Loading…
Add weightonly_wi2_afp32 and static_wi2_ai8 quantization schemes fro BatchMatMul and FC layers. Also add static_wi4_ai8 scheme for BatchMatMul.
#417 opened Mar 3, 2026 by copybara-service Bot Loading…
Add support for QUANTIZE from INT8/UINT8 to INT16.
#407 opened Feb 26, 2026 by copybara-service Bot Loading…
Update Gemma3n 2b quantization colab to utilize **RE-QUANTIZATION**
#377 opened Feb 13, 2026 by copybara-service Bot Loading…
Centralize the creation of Hadamard matrices, allow for a bit more than just powers of 2.
#373 opened Feb 10, 2026 by copybara-service Bot Loading…
ProTip! Adding no:label will show everything without a label.