-
Notifications
You must be signed in to change notification settings - Fork 14
Pull requests: google-ai-edge/ai-edge-quantizer
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Throw error if a single tensor is quantized multiple ways during static quantization.
#340
opened Oct 28, 2025 by
copybara-service
bot
Loading…
Update AI Edge Torch to use
BLOCKWISE_XX interface in AEQ to achieve blockwise quantization.
#339
opened Oct 28, 2025 by
copybara-service
bot
Loading…
Ensure quantization range always includes zero for both symmetric and asymmetric quantization.
#334
opened Oct 21, 2025 by
copybara-service
bot
Loading…
Make Pax quantizer configurable with custom quantization implementations
#319
opened Sep 17, 2025 by
copybara-service
bot
Loading…
Update quantization config for embedding Gemma.
#312
opened Sep 9, 2025 by
copybara-service
bot
Loading…
Add plumbing for blockwise for TFLite interpreter
#309
opened Sep 5, 2025 by
copybara-service
bot
Loading…
Add None check before dataclasses.replace.
#297
opened Aug 20, 2025 by
copybara-service
bot
Loading…
Fix a buffer sharing bug for composite op quantization
#274
opened Jun 23, 2025 by
copybara-service
bot
Loading…
Conditionally dynamically allocate TfLiteFloatArray data member.
#252
opened May 26, 2025 by
copybara-service
bot
Loading…
Implement Hadamard rotation reference as a custom op
#232
opened May 3, 2025 by
copybara-service
bot
Loading…
Fix incorrect im2col size allocation with INT4 filter
#158
opened Oct 16, 2024 by
copybara-service
bot
Loading…
Complete i4 FullyConnected support for TFLite
#155
opened Oct 5, 2024 by
copybara-service
bot
Loading…
Create a python schema_generated target on the compiler mlir side, and use that for odml/model_customization/quantization
#140
opened Sep 20, 2024 by
copybara-service
bot
Loading…
ProTip!
Adding no:label will show everything without a label.