All pull requests

Pull requests

• Internal

  #395·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Internal

  #394·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Internal

  #393·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Internal

  #392·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Internal

  #391·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Internal

  #390·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Internal

  #389·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Leave uncalibrated activations in float during ODML conversion.

  #388·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Add quantize_linen_class to quantize Linen classes directly.

  #387·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Locate weights by the module that declares them, not the one that reads them.

  #386·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Fix the degenerate-scale guard for float64 calibration arrays.

  #385·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Treat minimum and maximum as same-scale ops.

  #384·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Restart Qwix op ids on every module invocation.

  #383·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Apply per-tensor activation scales at the rank of the tensor being quantized.

  #382·copybara-service[bot] opened Sep 23, 2026Bot·

  ·

• Add Gemma 4 E2B MLP quantization and multi-pass sweep configuration.

  #381·copybara-service[bot] opened Sep 22, 2026Bot·

  ·

• Support microscaled multi-pass GEMM in QWIX with hardware FP8 YOLO accumulation.

  #380·copybara-service[bot] opened Sep 22, 2026Bot·

  ·

• Add Gemma 4 E2B MLP quantization and multi-pass sweep configuration.

  #375·copybara-service[bot] opened Sep 15, 2026Bot·

  ·

• Support hierarchical scaling with per-axis BF16 and subchannel microscaling in QWIX.

  #374·copybara-service[bot] opened Sep 15, 2026Bot·

  ·

• Support approximate INT8 multi-pass matrix multiplication in QWIX.

  #373·copybara-service[bot] opened Sep 15, 2026Bot·

  ·

• Support hybrid FP8 and 4-bit multi-pass matrix multiplication in QWIX.

  #372·copybara-service[bot] opened Sep 15, 2026Bot·

  ·

• Use jax.lax.scaled_dot for MXFP dot_general in Qwix instead of jax.nn.scaled_matmul that binds to cuDNN

  #369·copybara-service[bot] opened Sep 14, 2026Bot·

  ·

• Support configurable power-of-2 scaling ('oas' vs 'ceil') for floating-point microscaling in QWIX

  #366·copybara-service[bot] opened Sep 11, 2026Bot·

  ·

• feat(int4): add nibble_pack/unpack for true 0.5 B/elem int4 storage

  #329·lokic233 opened Jul 8, 2026·

  ·
  1

• docs: document MXFP numerics (mxfp8/mxfp4/nvfp4) and hardware dispatch

  #324·lokic233 opened Jul 6, 2026·

  ·
  2

• [pallas:mosaic] Migrated all uses of pltpu.emit_pipeline to explicit indices

  #322·copybara-service[bot] opened Jul 3, 2026Bot·

  ·