{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/i-bert-integer-only-bert-quantization","title":"I-BERT: Integer-only BERT Quantization","arxiv_id":"2101.01321","date":"2021-01-05","proceeding":null,"authors":["Sehoon Kim","Amir Gholami","Zhewei Yao","Michael W. Mahoney","Kurt Keutzer"],"abstract":"Transformer based models, like BERT and RoBERTa, have achieved state-of-the-art results in many Natural Language Processing tasks. However, their memory footprint, inference latency, and power consumption are prohibitive efficient inference at the edge, and even at the data center. While quantization can be a viable solution for this, previous work on quantizing Transformer based models use floating-point arithmetic during inference, which cannot efficiently utilize integer-only logical units such as the recent Turing Tensor Cores, or traditional integer-only ARM processors. In this work, we propose I-BERT, a novel quantization scheme for Transformer based models that quantizes the entire inference with integer-only arithmetic. Based on lightweight integer-only approximation methods for nonlinear operations, e.g., GELU, Softmax, and Layer Normalization, I-BERT performs an end-to-end integer-only BERT inference without any floating point calculation. We evaluate our approach on GLUE downstream tasks using RoBERTa-Base/Large. We show that for both cases, I-BERT achieves similar (and slightly higher) accuracy as compared to the full-precision baseline. Furthermore, our preliminary implementation of I-BERT shows a speedup of 2.4-4.0x for INT8 inference on a T4 GPU system as compared to FP32 inference. The framework has been developed in PyTorch and has been open-sourced.","url_abs":"https://arxiv.org/abs/2101.01321v3","url_pdf":"https://arxiv.org/pdf/2101.01321v3.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":"i-bert-integer-only-bert-quantization","repo_url":"https://github.com/kssteven418/I-BERT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"i-bert-integer-only-bert-quantization","repo_url":"https://github.com/huggingface/transformers/tree/master/src/transformers/models/ibert","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"i-bert-integer-only-bert-quantization","repo_url":"https://github.com/ucb-bar/gemmini","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"i-bert-integer-only-bert-quantization","repo_url":"https://github.com/2023-MindSpore-1/ms-code-222/tree/main/bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"i-bert-integer-only-bert-quantization","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"i-bert-integer-only-bert-quantization","repo_url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/ibert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"i-bert-integer-only-bert-quantization","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/ibert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"i-bert","method_name":"I-BERT"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[{"slug":"i-bert","name":"I-BERT","full_name":"I-BERT"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.01321","atlas_url":"https://app.syntology.ai/?focus=2101.01321","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2101.01321"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2101.01321\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2101.01321"},"call":"get_concepts_for_paper(arxiv_id=\"2101.01321\")"}],"by_repo":[{"repo":"kssteven418/I-BERT","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"huggingface/transformers","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["1706.03762","1910.03771","2006.03654","2010.01057"],"harvested_for_calls":[{"arxiv_id":"1706.03762","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1706.03762"},"call":"get_harvested_code_for_paper(arxiv_id=\"1706.03762\")"},{"arxiv_id":"1910.03771","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1910.03771"},"call":"get_harvested_code_for_paper(arxiv_id=\"1910.03771\")"},{"arxiv_id":"2006.03654","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2006.03654"},"call":"get_harvested_code_for_paper(arxiv_id=\"2006.03654\")"},{"arxiv_id":"2010.01057","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.01057"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.01057\")"}]},{"repo":"ucb-bar/gemmini","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2023-MindSpore-1/ms-code-222","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"2024-MindSpore-1/Code2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MindSpore-scientific-2/code-14","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pwc-1/Paper-9","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1909.13719"],"harvested_for_calls":[{"arxiv_id":"1909.13719","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.13719"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.13719\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f58fbef6af063f62b975433a37e9ae2c3866b8c75e7edadc513c8a00fc3ddaf0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}