{"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/8-bit-optimizers-via-block-wise-quantization","title":"8-bit Optimizers via Block-wise Quantization","arxiv_id":"2110.02861","date":"2021-10-06","proceeding":"ICLR 2022 4","authors":["Tim Dettmers","Mike Lewis","Sam Shleifer","Luke Zettlemoyer"],"abstract":"Stateful optimizers maintain gradient statistics over time, e.g., the exponentially smoothed sum (SGD with momentum) or squared sum (Adam) of past gradient values. This state can be used to accelerate optimization compared to plain stochastic gradient descent but uses memory that might otherwise be allocated to model parameters, thereby limiting the maximum size of models trained in practice. In this paper, we develop the first optimizers that use 8-bit statistics while maintaining the performance levels of using 32-bit optimizer states. To overcome the resulting computational, quantization, and stability challenges, we develop block-wise dynamic quantization. Block-wise quantization divides input tensors into smaller blocks that are independently quantized. Each block is processed in parallel across cores, yielding faster optimization and high precision quantization. To maintain stability and performance, we combine block-wise quantization with two additional changes: (1) dynamic quantization, a form of non-linear optimization that is precise for both large and small magnitude values, and (2) a stable embedding layer to reduce gradient variance that comes from the highly non-uniform distribution of input tokens in language models. As a result, our 8-bit optimizers maintain 32-bit performance with a small fraction of the memory footprint on a range of tasks, including 1.5B parameter language modeling, GLUE finetuning, ImageNet classification, WMT'14 machine translation, MoCo v2 contrastive ImageNet pretraining+finetuning, and RoBERTa pretraining, without changes to the original optimizer hyperparameters. We open-source our 8-bit optimizers as a drop-in replacement that only requires a two-line code change.","url_abs":"https://arxiv.org/abs/2110.02861v2","url_pdf":"https://arxiv.org/pdf/2110.02861v2.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":"8-bit-optimizers-via-block-wise-quantization","repo_url":"https://github.com/facebookresearch/bitsandbytes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"8-bit-optimizers-via-block-wise-quantization","repo_url":"https://github.com/nvlabs/coat","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"8-bit-optimizers-via-block-wise-quantization","repo_url":"https://github.com/timdettmers/bitsandbytes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"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":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"infonce","method_name":"InfoNCE"},{"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":"moco","method_name":"MoCo"},{"method_slug":"moco-v2","method_name":"MoCo v2"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"random-gaussian-blur","method_name":"Random Gaussian Blur"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.02861","atlas_url":"https://app.syntology.ai/?focus=2110.02861","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":"2110.02861"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.02861\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.02861"},"call":"get_concepts_for_paper(arxiv_id=\"2110.02861\")"}],"by_repo":[{"repo":"facebookresearch/bitsandbytes","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"nvlabs/coat","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.19313"],"harvested_for_calls":[{"arxiv_id":"2410.19313","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.19313"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.19313\")"}]},{"repo":"timdettmers/bitsandbytes","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":4,"harvested_for":["2208.07339","2211.05100","2304.13013","2309.01507"],"harvested_for_calls":[{"arxiv_id":"2208.07339","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2208.07339"},"call":"get_harvested_code_for_paper(arxiv_id=\"2208.07339\")"},{"arxiv_id":"2211.05100","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2211.05100"},"call":"get_harvested_code_for_paper(arxiv_id=\"2211.05100\")"},{"arxiv_id":"2304.13013","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.13013"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.13013\")"},{"arxiv_id":"2309.01507","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.01507"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.01507\")"}]}],"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":"20756c4ffd7a3c02cf28fb7567e9918985ab24d8615ec6cebc82cefe0d090fe3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}