Tag
Introduces Variable Bit-width Quantization (VBQ), a training-time method where each group of 64 weights learns its own bit-width (1,2,4,8) via Gumbel-Softmax relaxation. VBQ discovers a heterogeneous allocation that yields a 'bigger-but-smaller' regime, e.g., a 131M parameter model at 1.82 mean bits beats a 55M FP16 model while using less storage, and a 1.46B model matches a 593M FP16 with ~3.7x less storage.
A novel end-to-end framework for LLM compression that jointly optimizes structural pruning and mixed-precision quantization, achieving significant perplexity reductions and speedups over state-of-the-art methods, especially at ultra-low bit precisions.
This paper systematically studies HiF8 W8A8 quantization-aware training for OpenPangu-Embedded-1B, identifying and addressing failure modes such as amax saturation and catastrophic forgetting, achieving near-lossless performance with a 64-step max-algorithm DTS strategy and a 500-step BF16 warmup.