{"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/svd-llm-v2-optimizing-singular-value","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","arxiv_id":"2503.12340","date":"2025-03-16","proceeding":null,"authors":["Xin Wang","Samiul Alam","Zhongwei Wan","Hui Shen","Mi Zhang"],"abstract":"Despite significant advancements, the practical deployment of Large Language Models (LLMs) is often hampered by their immense sizes, highlighting the need for effective compression techniques. Singular Value Decomposition (SVD) is a promising LLM compression technique. However, existing SVD-based compression methods fall short in reducing truncation losses, leading to less competitive performance in compressed models. In this work, we introduce SVD-LLM V2, a SVD-based LLM compression method that optimizes singular value truncation in SVD compression with two techniques. First, SVD-LLM V2 proposes to use theoretical truncation loss of weight matrices to assign a unique compression ratio to each weight matrix at different layers to accommodate weight redundancy heterogeneity. Second, SVD-LLM V2 proposes loss-optimized weight truncation to ensure that the truncated singular values result in a lower and more stable truncation loss in practice. We evaluate SVD-LLM V2 on ten datasets and five LLMs at various scales. Our results show SVD-LLM V2 outperforms state-of-the-art SVD-based LLM compression methods. Our code is available at https://github.com/AIoT-MLSys-Lab/SVD-LLM","url_abs":"https://arxiv.org/abs/2503.12340v1","url_pdf":"https://arxiv.org/pdf/2503.12340v1.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":"svd-llm-v2-optimizing-singular-value","repo_url":"https://github.com/aiot-mlsys-lab/svd-llm","is_official":1,"mentioned_in_paper":1,"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":"large-language-model","task_name":"Large Language Model"},{"task_slug":"model-compression","task_name":"Model Compression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.12340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12340"}},"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/aiot-mlsys-lab/svd-llm","reach":null}],"summary":{"ran":6,"ran_fixture":2,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":12,"ran":9,"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":"c4daf2f7ed4b51f9","entry":"LlamaRotaryEmbedding","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c4daf2f7ed4b51f9"}},{"code_sha256_prefix":"1b2e87c411e2d8bc","entry":"MistralRotaryEmbedding","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1b2e87c411e2d8bc"}},{"code_sha256_prefix":"041ad30174c9bdee","entry":"SVDOPTAttention","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"041ad30174c9bdee"}},{"code_sha256_prefix":"8a5b8f50673d8352","entry":"SVD_LlamaAttention","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.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":"8a5b8f50673d8352"}},{"code_sha256_prefix":"77e1446ab4ce2b75","entry":"SVD_LlamaMLP","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.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":"77e1446ab4ce2b75"}},{"code_sha256_prefix":"3009ebbba1aa5922","entry":"SVD_MistralMLP","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3009ebbba1aa5922"}},{"code_sha256_prefix":"af9e30f5a1fe133e","entry":"apply_rotary_pos_emb","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af9e30f5a1fe133e"}},{"code_sha256_prefix":"25ef0712acc702e7","entry":"repeat_kv","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"25ef0712acc702e7"}},{"code_sha256_prefix":"2a2393c46243da08","entry":"rotate_half","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2a2393c46243da08"}},{"code_sha256_prefix":"88545df842057010","entry":"SVDOPTDecoderLayer","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.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":"88545df842057010"}},{"code_sha256_prefix":"656c1a145aa666cb","entry":"SVD_MistralAttention","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.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":"656c1a145aa666cb"}},{"code_sha256_prefix":"d0b633b47c9a7133","entry":"whitening_local_update","repo":"aiot-mlsys-lab/svd-llm","repo_kind":"official","path":"SVDLLM.py","file_url":"https://github.com/aiot-mlsys-lab/svd-llm/blob/HEAD/SVDLLM.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":"d0b633b47c9a7133"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}