{"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/f8net-fixed-point-8-bit-only-multiplication-1","title":"F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization","arxiv_id":"2202.05239","date":"2022-02-10","proceeding":"ICLR 2022 4","authors":["Qing Jin","Jian Ren","Richard Zhuang","Sumant Hanumante","Zhengang Li","Zhiyu Chen","Yanzhi Wang","Kaiyuan Yang","Sergey Tulyakov"],"abstract":"Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision models. To reduce it, existing quantization approaches require high-precision INT32 or full-precision multiplication during inference for scaling or dequantization. This introduces a noticeable cost in terms of memory, speed, and required energy. To tackle these issues, we present F8Net, a novel quantization framework consisting of only fixed-point 8-bit multiplication. To derive our method, we first discuss the advantages of fixed-point multiplication with different formats of fixed-point numbers and study the statistical behavior of the associated fixed-point numbers. Second, based on the statistical and algorithmic analysis, we apply different fixed-point formats for weights and activations of different layers. We introduce a novel algorithm to automatically determine the right format for each layer during training. Third, we analyze a previous quantization algorithm -- parameterized clipping activation (PACT) -- and reformulate it using fixed-point arithmetic. Finally, we unify the recently proposed method for quantization fine-tuning and our fixed-point approach to show the potential of our method. We verify F8Net on ImageNet for MobileNet V1/V2 and ResNet18/50. Our approach achieves comparable and better performance, when compared not only to existing quantization techniques with INT32 multiplication or floating-point arithmetic, but also to the full-precision counterparts, achieving state-of-the-art performance.","url_abs":"https://arxiv.org/abs/2202.05239v1","url_pdf":"https://arxiv.org/pdf/2202.05239v1.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":[{"paper_slug":"f8net-fixed-point-8-bit-only-multiplication-1","repo_url":"https://github.com/snap-research/f8net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2202.05239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.05239"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/snap-research/f8net","reach":null}],"summary":{"ran_draft_wrong":1,"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":5,"samples":[{"code_sha256_prefix":"b8d76d790125090f","entry":"fraclen_gridsearch","repo":"snap-research/f8net","repo_kind":"official","path":"models/fix_quant_ops.py","file_url":"https://github.com/snap-research/f8net/blob/HEAD/models/fix_quant_ops.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b8d76d790125090f"}},{"code_sha256_prefix":"19fd1ae58568c965","entry":"metric2fraclen","repo":"snap-research/f8net","repo_kind":"official","path":"models/fix_quant_ops.py","file_url":"https://github.com/snap-research/f8net/blob/HEAD/models/fix_quant_ops.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"19fd1ae58568c965"}},{"code_sha256_prefix":"9039c3687fece59e","entry":"ReLUClipFXQConvBN","repo":"snap-research/f8net","repo_kind":"official","path":"models/fix_quant_ops.py","file_url":"https://github.com/snap-research/f8net/blob/HEAD/models/fix_quant_ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9039c3687fece59e"}},{"code_sha256_prefix":"9f7456e6cfd981c1","entry":"fix_quant","repo":"snap-research/f8net","repo_kind":"official","path":"models/fix_quant_ops.py","file_url":"https://github.com/snap-research/f8net/blob/HEAD/models/fix_quant_ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9f7456e6cfd981c1"}},{"code_sha256_prefix":"944dc529bfd9f6d4","entry":"q_k","repo":"snap-research/f8net","repo_kind":"official","path":"models/fix_quant_ops.py","file_url":"https://github.com/snap-research/f8net/blob/HEAD/models/fix_quant_ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"944dc529bfd9f6d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}