{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/taq-dit-time-aware-quantization-for-diffusion","title":"TaQ-DiT: Time-aware Quantization for Diffusion Transformers","arxiv_id":"2411.14172","date":"2024-11-21","proceeding":null,"authors":["Xinyan Liu","Huihong Shi","Yang Xu","Zhongfeng Wang"],"abstract":"Transformer-based diffusion models, dubbed Diffusion Transformers (DiTs), have achieved state-of-the-art performance in image and video generation tasks. However, their large model size and slow inference speed limit their practical applications, calling for model compression methods such as quantization. Unfortunately, existing DiT quantization methods overlook (1) the impact of reconstruction and (2) the varying quantization sensitivities across different layers, which hinder their achievable performance. To tackle these issues, we propose innovative time-aware quantization for DiTs (TaQ-DiT). Specifically, (1) we observe a non-convergence issue when reconstructing weights and activations separately during quantization and introduce a joint reconstruction method to resolve this problem. (2) We discover that Post-GELU activations are particularly sensitive to quantization due to their significant variability across different denoising steps as well as extreme asymmetries and variations within each step. To address this, we propose time-variance-aware transformations to facilitate more effective quantization. Experimental results show that when quantizing DiTs' weights to 4-bit and activations to 8-bit (W4A8), our method significantly surpasses previous quantization methods.","url_abs":"https://arxiv.org/abs/2411.14172v1","url_pdf":"https://arxiv.org/pdf/2411.14172v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.14172","atlas_url":"https://app.syntology.ai/?focus=2411.14172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14172"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/6xy-liu/Taq-DiT","reach":null}],"summary":{"ran":2,"ran_draft_wrong":3,"unverified":2},"by_repo_kind":{"found_in_text":{"samples":7,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"119e117e97e53371","entry":"ObserverBase","repo":"6xy-liu/Taq-DiT","repo_kind":"found_in_text","path":"quant/quantization/fake_quant.py","file_url":"https://github.com/6xy-liu/Taq-DiT/blob/HEAD/quant/quantization/fake_quant.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"119e117e97e53371"}},{"code_sha256_prefix":"f352d07e60e42108","entry":"QuantizeBase","repo":"6xy-liu/Taq-DiT","repo_kind":"found_in_text","path":"quant/quantization/fake_quant.py","file_url":"https://github.com/6xy-liu/Taq-DiT/blob/HEAD/quant/quantization/fake_quant.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f352d07e60e42108"}},{"code_sha256_prefix":"ba1ffd12796f5219","entry":"fake_quantize_learnable_per_channel_affine_training","repo":"6xy-liu/Taq-DiT","repo_kind":"found_in_text","path":"quant/quantization/fake_quant.py","file_url":"https://github.com/6xy-liu/Taq-DiT/blob/HEAD/quant/quantization/fake_quant.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ba1ffd12796f5219"}},{"code_sha256_prefix":"9eaea08ad40b7c03","entry":"fake_quantize_learnable_per_tensor_affine_training","repo":"6xy-liu/Taq-DiT","repo_kind":"found_in_text","path":"quant/quantization/fake_quant.py","file_url":"https://github.com/6xy-liu/Taq-DiT/blob/HEAD/quant/quantization/fake_quant.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9eaea08ad40b7c03"}},{"code_sha256_prefix":"043c3be8a95e065c","entry":"grad_scale","repo":"6xy-liu/Taq-DiT","repo_kind":"found_in_text","path":"quant/quantization/fake_quant.py","file_url":"https://github.com/6xy-liu/Taq-DiT/blob/HEAD/quant/quantization/fake_quant.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"043c3be8a95e065c"}},{"code_sha256_prefix":"5f945957d82c3552","entry":"LSQFakeQuantize","repo":"6xy-liu/Taq-DiT","repo_kind":"found_in_text","path":"quant/quantization/fake_quant.py","file_url":"https://github.com/6xy-liu/Taq-DiT/blob/HEAD/quant/quantization/fake_quant.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f945957d82c3552"}},{"code_sha256_prefix":"47345a9d948debda","entry":"global_val","repo":"6xy-liu/Taq-DiT","repo_kind":"found_in_text","path":"quant/quantization/fake_quant.py","file_url":"https://github.com/6xy-liu/Taq-DiT/blob/HEAD/quant/quantization/fake_quant.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"47345a9d948debda"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}