3 Pull requests merged by 3 people

• [Torch] AWQ support for WeightCompression

  #3279 merged Feb 21, 2025

• Bump transformers version

  #3272 merged Feb 21, 2025

• Bump pydot

  #3300 merged Feb 21, 2025

9 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• [PT2] cache for shared parameters

  #3297 commented on Feb 21, 2025 • 4 new comments

• [Good First Issue][NNCF]: Add ONNX support of data-free Weight Compression Algorithm

  #3273 commented on Feb 21, 2025 • 0 new comments

• RuntimeError: CUDA is available for PyTorch, but NNcF could not compile GPu quan tization extensions.

  #3033 commented on Feb 21, 2025 • 0 new comments

• [Torch] Bump PyTorch Version to 2.6.0

  #3253 commented on Feb 21, 2025 • 0 new comments

• [OpenVINOQuantizer] Mark quantizer and quantize_pt2e as API

  #3277 commented on Feb 21, 2025 • 0 new comments

• llm weight compression tool

  #3290 commented on Feb 21, 2025 • 0 new comments

• OV data-free mixed precision assignment running time improvement

  #3292 commented on Feb 21, 2025 • 0 new comments

• [PT2] weight_compression

  #3293 commented on Feb 21, 2025 • 0 new comments

• Remove upper bound for matplotlib

  #3299 commented on Feb 21, 2025 • 0 new comments