REVIEW 6 cited by
Scaling Law for Quantization-Aware Training
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Scaling Law for Quantization-Aware Training
read the original abstract
Large language models (LLMs) demand substantial computational and memory resources, creating deployment challenges. Quantization-aware training (QAT) addresses these challenges by reducing model precision while maintaining performance. However, the scaling behavior of QAT, especially at 4-bit precision (W4A4), is not well understood. Existing QAT scaling laws often ignore key factors such as the number of training tokens and quantization granularity, which limits their applicability. This paper proposes a unified scaling law for QAT that models quantization error as a function of model size, training data volume, and quantization group size. Through 268 QAT experiments, we show that quantization error decreases as model size increases, but rises with more training tokens and coarser quantization granularity. To identify the sources of W4A4 quantization error, we decompose it into weight and activation components. Both components follow the overall trend of W4A4 quantization error, but with different sensitivities. Specifically, weight quantization error increases more rapidly with more training tokens. Further analysis shows that the activation quantization error in the FC2 layer, caused by outliers, is the primary bottleneck of W4A4 QAT quantization error. By applying mixed-precision quantization to address this bottleneck, we demonstrate that weight and activation quantization errors can converge to similar levels. Additionally, with more training data, weight quantization error eventually exceeds activation quantization error, suggesting that reducing weight quantization error is also important in such scenarios. These findings offer key insights for improving QAT research and development.
Forward citations
Cited by 6 Pith papers
-
APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing
APEX4 co-designs pure INT4 GEMM kernels with ρ-aware granularity adaptation to deliver up to 2.09× end-to-end speedup on GPUs with low ρ while keeping LLaMA-2-70B perplexity within 0.63 of FP16.
-
When Flat Minima Fail: Characterizing INT4 Quantization Collapse After FP32 Convergence
FP32-converged language models enter a post-convergence phase where INT4 quantization error explodes while FP32 perplexity remains stable, with onset tied to fine convergence rather than learning rate decay.
-
APEX4: Efficient Pure W4A4 LLM Inference via Intra-SM Compute Rebalancing
APEX4 co-designs pure INT4 GEMM kernels with ρ-aware granularity adaptation to deliver up to 2.09× end-to-end speedup on GPUs with low ρ while keeping perplexity within 0.63 of FP16 on LLaMA-2-70B.
-
Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs
A conditional scaling law fitted on over 200 models from 80M to 3B parameters identifies architectures that deliver up to 2.1% higher accuracy and 42% higher inference throughput than LLaMA-3.2 under the same training budget.
-
Efficient Reasoning on the Edge
LoRA adapters, budget-forced GRPO, dynamic switching, parallel verification and FPTQuant enable practical chain-of-thought reasoning on quantized Qwen2.5-7B for edge devices.
-
NVIDIA Nemotron 3: Efficient and Open Intelligence
NVIDIA releases the Nemotron 3 model family with hybrid Mamba-Transformer architecture, LatentMoE, NVFP4 training, MTP layers, and multi-environment RL post-training for reasoning and agentic tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.