{"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/scalify-scale-propagation-for-efficient-low","title":"Scalify: scale propagation for efficient low-precision LLM training","arxiv_id":"2407.17353","date":"2024-07-24","proceeding":null,"authors":["Paul Balança","Sam Hosegood","Carlo Luschi","Andrew Fitzgibbon"],"abstract":"Low-precision formats such as float8 have been introduced in machine learning accelerated hardware to improve computational efficiency for large language models training and inference. Nevertheless, adoption by the ML community has been slowed down by the complex, and sometimes brittle, techniques required to match higher precision training accuracy. In this work, we present Scalify, a end-to-end scale propagation paradigm for computational graphs, generalizing and formalizing existing tensor scaling methods. Experiment results show that Scalify supports out-of-the-box float8 matrix multiplication and gradients representation, as well as float16 optimizer state storage. Our JAX implementation of Scalify is open-sourced at https://github.com/graphcore-research/jax-scalify","url_abs":"https://arxiv.org/abs/2407.17353v1","url_pdf":"https://arxiv.org/pdf/2407.17353v1.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":"scalify-scale-propagation-for-efficient-low","repo_url":"https://github.com/graphcore-research/jax-scalify","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.17353","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17353"}},"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":"deterministic:regex_extraction","url":"https://github.com/graphcore-research/jax-scalify","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"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":"38d4748ec4e5294b","entry":"get_debug_callback_effect","repo":"graphcore-research/jax-scalify","repo_kind":"official","path":"jax_scalify/core/debug.py","file_url":"https://github.com/graphcore-research/jax-scalify/blob/HEAD/jax_scalify/core/debug.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"38d4748ec4e5294b"}},{"code_sha256_prefix":"c3405e97962dbc40","entry":"get_numpy_api","repo":"graphcore-research/jax-scalify","repo_kind":"official","path":"jax_scalify/core/typing.py","file_url":"https://github.com/graphcore-research/jax-scalify/blob/HEAD/jax_scalify/core/typing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c3405e97962dbc40"}},{"code_sha256_prefix":"6de40b822f908408","entry":"python_scalar_as_numpy","repo":"graphcore-research/jax-scalify","repo_kind":"official","path":"jax_scalify/core/utils.py","file_url":"https://github.com/graphcore-research/jax-scalify/blob/HEAD/jax_scalify/core/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6de40b822f908408"}},{"code_sha256_prefix":"10666eae469c2eed","entry":"set_scaling_abstract_eval","repo":"graphcore-research/jax-scalify","repo_kind":"official","path":"jax_scalify/lax/base_scaling_primitives.py","file_url":"https://github.com/graphcore-research/jax-scalify/blob/HEAD/jax_scalify/lax/base_scaling_primitives.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"10666eae469c2eed"}},{"code_sha256_prefix":"ccdb8081b32f9f85","entry":"debug_callback","repo":"graphcore-research/jax-scalify","repo_kind":"official","path":"jax_scalify/core/debug.py","file_url":"https://github.com/graphcore-research/jax-scalify/blob/HEAD/jax_scalify/core/debug.py","link_basis":"first_harvest_node","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":"ccdb8081b32f9f85"}},{"code_sha256_prefix":"ce0d08e42d91f35b","entry":"debug_callback_grad","repo":"graphcore-research/jax-scalify","repo_kind":"official","path":"jax_scalify/ops/debug.py","file_url":"https://github.com/graphcore-research/jax-scalify/blob/HEAD/jax_scalify/ops/debug.py","link_basis":"first_harvest_node","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":"ce0d08e42d91f35b"}},{"code_sha256_prefix":"7c5e52fa74a762c4","entry":"debug_callback_grad_fwd","repo":"graphcore-research/jax-scalify","repo_kind":"official","path":"jax_scalify/ops/debug.py","file_url":"https://github.com/graphcore-research/jax-scalify/blob/HEAD/jax_scalify/ops/debug.py","link_basis":"first_harvest_node","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":"7c5e52fa74a762c4"}},{"code_sha256_prefix":"4fbd7e698d2b18f7","entry":"dtype_exponent_mask","repo":"graphcore-research/jax-scalify","repo_kind":"official","path":"jax_scalify/core/pow2.py","file_url":"https://github.com/graphcore-research/jax-scalify/blob/HEAD/jax_scalify/core/pow2.py","link_basis":"first_harvest_node","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":"4fbd7e698d2b18f7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}