{"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/attention-aware-post-training-quantization","title":"Attention-aware Post-training Quantization without Backpropagation","arxiv_id":"2406.13474","date":"2024-06-19","proceeding":null,"authors":["Junhan Kim","Ho-young Kim","Eulrang Cho","Chungman Lee","Joonyoung Kim","Yongkweon Jeon"],"abstract":"Quantization is a promising solution for deploying large-scale language models (LLMs) on resource-constrained devices. Existing quantization approaches, however, rely on gradient-based optimization, regardless of it being post-training quantization (PTQ) or quantization-aware training (QAT), which becomes problematic for hyper-scale LLMs with billions of parameters. This overhead can be alleviated via recently proposed backpropagation-free PTQ methods; however, their performance is somewhat limited by their lack of consideration of inter-layer dependencies. In this paper, we thus propose a novel PTQ algorithm that considers inter-layer dependencies without relying on backpropagation. The fundamental concept involved is the development of attention-aware Hessian matrices, which facilitates the consideration of inter-layer dependencies within the attention module. Extensive experiments demonstrate that the proposed algorithm significantly outperforms conventional PTQ methods, particularly for low bit-widths.","url_abs":"https://arxiv.org/abs/2406.13474v1","url_pdf":"https://arxiv.org/pdf/2406.13474v1.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":[],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.13474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13474"}},"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/SamsungLabs/BoA","reach":null}],"summary":{"ran":1,"ran_draft_wrong":4,"ran_fixture":5,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":11,"ran":10,"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":11,"samples":[{"code_sha256_prefix":"30794ea4f77e617d","entry":"BoA","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.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":"30794ea4f77e617d"}},{"code_sha256_prefix":"f454b164e03e97cd","entry":"damping","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f454b164e03e97cd"}},{"code_sha256_prefix":"e720961192f8cc13","entry":"fake_quantize","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e720961192f8cc13"}},{"code_sha256_prefix":"e7cdd0d8ff38c485","entry":"filter_dead_neuron","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e7cdd0d8ff38c485"}},{"code_sha256_prefix":"b4ee4d03c2667d47","entry":"get_cholesky_of_inverse","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b4ee4d03c2667d47"}},{"code_sha256_prefix":"b6a41484b3b9b656","entry":"quantize","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b6a41484b3b9b656"}},{"code_sha256_prefix":"43c717cebadf7e91","entry":"reorder_col","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"43c717cebadf7e91"}},{"code_sha256_prefix":"c9f502a6a946cd16","entry":"reorder_row","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c9f502a6a946cd16"}},{"code_sha256_prefix":"bc61e2d7ad94414b","entry":"reverse_reorder_col","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bc61e2d7ad94414b"}},{"code_sha256_prefix":"61e1feb02fd713b4","entry":"reverse_reorder_row","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"61e1feb02fd713b4"}},{"code_sha256_prefix":"b9b9db4928482dd1","entry":"cleanup_memory","repo":"SamsungLabs/BoA","repo_kind":"found_in_text","path":"quantizers/boa.py","file_url":"https://github.com/SamsungLabs/BoA/blob/HEAD/quantizers/boa.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":"b9b9db4928482dd1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}