{"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/fp8-formats-for-deep-learning","title":"FP8 Formats for Deep Learning","arxiv_id":"2209.05433","date":"2022-09-12","proceeding":null,"authors":["Paulius Micikevicius","Dusan Stosic","Neil Burgess","Marius Cornea","Pradeep Dubey","Richard Grisenthwaite","Sangwon Ha","Alexander Heinecke","Patrick Judd","John Kamalu","Naveen Mellempudi","Stuart Oberman","Mohammad Shoeybi","Michael Siu","Hao Wu"],"abstract":"FP8 is a natural progression for accelerating deep learning training inference beyond the 16-bit formats common in modern processors. In this paper we propose an 8-bit floating point (FP8) binary interchange format consisting of two encodings - E4M3 (4-bit exponent and 3-bit mantissa) and E5M2 (5-bit exponent and 2-bit mantissa). While E5M2 follows IEEE 754 conventions for representatio of special values, E4M3's dynamic range is extended by not representing infinities and having only one mantissa bit-pattern for NaNs. We demonstrate the efficacy of the FP8 format on a variety of image and language tasks, effectively matching the result quality achieved by 16-bit training sessions. Our study covers the main modern neural network architectures - CNNs, RNNs, and Transformer-based models, leaving all the hyperparameters unchanged from the 16-bit baseline training sessions. Our training experiments include large, up to 175B parameter, language models. We also examine FP8 post-training-quantization of language models trained using 16-bit formats that resisted fixed point int8 quantization.","url_abs":"https://arxiv.org/abs/2209.05433v2","url_pdf":"https://arxiv.org/pdf/2209.05433v2.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":"fp8-formats-for-deep-learning","repo_url":"https://github.com/intellabs/fp8-emulation-toolkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"fp8-formats-for-deep-learning","repo_url":"https://github.com/nvidia/transformerengine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"fp8-formats-for-deep-learning","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":"fp8-formats-for-deep-learning","repo_url":"https://github.com/pytorch/ao","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.05433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.05433"}},"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/nvlabs/coat","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvidia/transformerengine","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pytorch/ao","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intellabs/fp8-emulation-toolkit","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"7fd2e1e68bc3372f","entry":"all_files_in_dir","repo":"nvidia/transformerengine","repo_kind":"listed","path":"build_tools/utils.py","file_url":"https://github.com/nvidia/transformerengine/blob/HEAD/build_tools/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7fd2e1e68bc3372f"}},{"code_sha256_prefix":"2491511b79d5aa62","entry":"dump_kernel_counts","repo":"nvidia/transformerengine","repo_kind":"listed","path":"benchmarks/profile_rht_cast_swizzle_fusion.py","file_url":"https://github.com/nvidia/transformerengine/blob/HEAD/benchmarks/profile_rht_cast_swizzle_fusion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2491511b79d5aa62"}},{"code_sha256_prefix":"ec12d51e3d0d52ba","entry":"get_build_ext","repo":"nvidia/transformerengine","repo_kind":"listed","path":"build_tools/build_ext.py","file_url":"https://github.com/nvidia/transformerengine/blob/HEAD/build_tools/build_ext.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec12d51e3d0d52ba"}},{"code_sha256_prefix":"eb194c4d49f9493a","entry":"nccl_ep_enabled","repo":"nvidia/transformerengine","repo_kind":"listed","path":"build_tools/utils.py","file_url":"https://github.com/nvidia/transformerengine/blob/HEAD/build_tools/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eb194c4d49f9493a"}},{"code_sha256_prefix":"d726e43ffe51bcf4","entry":"remove_dups","repo":"nvidia/transformerengine","repo_kind":"listed","path":"build_tools/utils.py","file_url":"https://github.com/nvidia/transformerengine/blob/HEAD/build_tools/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d726e43ffe51bcf4"}},{"code_sha256_prefix":"ec96f6c9e40998bf","entry":"setup_jax_extension","repo":"nvidia/transformerengine","repo_kind":"listed","path":"build_tools/jax.py","file_url":"https://github.com/nvidia/transformerengine/blob/HEAD/build_tools/jax.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ec96f6c9e40998bf"}},{"code_sha256_prefix":"b6b66114e7f5ad56","entry":"setup_pytorch_extension","repo":"nvidia/transformerengine","repo_kind":"listed","path":"build_tools/pytorch.py","file_url":"https://github.com/nvidia/transformerengine/blob/HEAD/build_tools/pytorch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b6b66114e7f5ad56"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}