PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
Update publication dates in README and add recipe configuration detai… (#1329)
Xin He46224d4aec23
diff --git a/README.md b/README.mdindex bd1eb06ff..6875c8533 100644--- a/README.md+++ b/README.md@@ -355,13 +355,13 @@ print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50)[0]))## Publications & Events-[SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs](https://arxiv.org/abs/2512.04746) (202512 paper)+[SignRoundV2: Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs](https://arxiv.org/abs/2512.04746) (2025.12 paper)-[Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLM](https://aclanthology.org/2024.findings-emnlp.662/) (202309 paper)+[Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLM](https://aclanthology.org/2024.findings-emnlp.662/) (2023.09 paper)-[TEQ: Trainable Equivalent Transformation for Quantization of LLMs](https://arxiv.org/abs/2310.10944) (202310 paper)+[TEQ: Trainable Equivalent Transformation for Quantization of LLMs](https://arxiv.org/abs/2310.10944) (2023.10 paper)-[Effective Post-Training Quantization for Large Language Models](https://medium.com/intel-analytics-software/effective-post-training-quantization-for-large-language-models-with-enhanced-smoothquant-approach-93e9d104fb98) (202304 blog)+[Effective Post-Training Quantization for Large Language Models](https://medium.com/intel-analytics-software/effective-post-training-quantization-for-large-language-models-with-enhanced-smoothquant-approach-93e9d104fb98) (2023.04 blog)Check out [Full Publication List](./docs/publication_list.md).diff --git a/docs/step_by_step.md b/docs/step_by_step.mdindex 519d82d2f..54c47a2f2 100644--- a/docs/step_by_step.md+++ b/docs/step_by_step.md@@ -274,6 +274,17 @@ ar.quantize_and_save(output_dir, format="auto_round")In conclusion, we recommend using **auto-round for W4A16 and auto-round-best for W2A16**. However, you may adjust theconfiguration to suit your specific requirements and available resources.+<details>+ <summary>Recipe Configuration Details</summary>++| Recipe | batch_size | iters | seqlen | nsamples | lr |+|---------|------------|-------|--------|----------|-------|+| default | 8 | 200 | 2048 | 128 | None |+| best | 8 | 1000 | 2048 | 512 | None |+| light | 8 | 50 | 2048 | 128 | 5e-3 |++</details>+W4G128 Average Accuracy of 13 tasks and Time Cost Results(Testing was conducted on the Nvidia A100 80G using the versionof PyTorch 2.6.0 with enable_torch_compile):