{"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/microscopiq-accelerating-foundational-models","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","arxiv_id":"2411.05282","date":"2024-11-08","proceeding":null,"authors":["Akshat Ramachandran","Souvik Kundu","Tushar Krishna"],"abstract":"Quantization of foundational models (FMs) is significantly more challenging than traditional DNNs due to the emergence of large magnitude values called outliers. Existing outlier-aware algorithm-architecture co-design techniques either use mixed-precision, retaining outliers at high precision but compromise hardware efficiency, or quantize inliers and outliers at the same precision, improving hardware efficiency at the cost of accuracy. To address this mutual exclusivity, we propose MicroScopiQ, a novel co-design technique that leverages pruning to complement outlier-aware quantization. MicroScopiQ retains outliers at higher precision while pruning a certain fraction of least important weights to distribute the additional outlier bits; ensuring high accuracy, aligned memory and hardware efficiency. We design a high-throughput, low overhead accelerator architecture composed of multi-precision INT processing elements and a network-on-chip called ReCoN that efficiently abstracts the complexity of supporting high-precision outliers. Additionally, unlike prior techniques, MicroScopiQ does not assume any locality of outlier weights, enabling applicability to a broad range of FMs. Extensive experiments across diverse quantization settings demonstrate that MicroScopiQ achieves state-of-the-art quantization accuracy, while delivering up to 3x faster inference and 2x lower energy consumption compared to existing alternatives. Code is available at: https://github.com/georgia-tech-synergy-lab/MicroScopiQ-LLM-Quantization","url_abs":"https://arxiv.org/abs/2411.05282v4","url_pdf":"https://arxiv.org/pdf/2411.05282v4.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":"microscopiq-accelerating-foundational-models","repo_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.05282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05282"}},"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/georgia-tech-synergy-lab/microscopiq-llm-quantization","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"unverified":10},"by_repo_kind":{"official":{"samples":12,"ran":2,"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":"a9e7f2cdf016b88b","entry":"find_layers","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"utils/modelutils.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/utils/modelutils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9e7f2cdf016b88b"}},{"code_sha256_prefix":"887f43fe08a6472d","entry":"get_opt","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"llm/opt.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/llm/opt.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"887f43fe08a6472d"}},{"code_sha256_prefix":"b98e145c4c83940d","entry":"analyze_outliers_olive","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"outlier_profiling/profiler.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/outlier_profiling/profiler.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b98e145c4c83940d"}},{"code_sha256_prefix":"88176b06dfb6df3e","entry":"compare_models_and_check_nans","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"llm/opt_direct.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/llm/opt_direct.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"88176b06dfb6df3e"}},{"code_sha256_prefix":"b6a8148f2f12adc9","entry":"evaluate_pred_answer","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"kv_quant/evaluation_gsm8k.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/kv_quant/evaluation_gsm8k.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6a8148f2f12adc9"}},{"code_sha256_prefix":"d1d25542bf6a73b0","entry":"get_llama","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"llm/llama.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/llm/llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d1d25542bf6a73b0"}},{"code_sha256_prefix":"494a1f0c452b05c6","entry":"layer_norm","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"number_system/mx/layernorm.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/number_system/mx/layernorm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"494a1f0c452b05c6"}},{"code_sha256_prefix":"c6cb1685a5860766","entry":"llama_sequential","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"llm/llama.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/llm/llama.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6cb1685a5860766"}},{"code_sha256_prefix":"5a1ab8a11275fe3d","entry":"opt_pack3","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"llm/opt.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/llm/opt.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a1ab8a11275fe3d"}},{"code_sha256_prefix":"3ef2f25d56625af9","entry":"opt_sequential","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"llm/opt.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/llm/opt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ef2f25d56625af9"}},{"code_sha256_prefix":"d93eb10d932ff2c8","entry":"parse_pred_ans","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"kv_quant/evaluation_gsm8k.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/kv_quant/evaluation_gsm8k.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d93eb10d932ff2c8"}},{"code_sha256_prefix":"b6065f749757a201","entry":"test_answer","repo":"georgia-tech-synergy-lab/microscopiq-llm-quantization","repo_kind":"official","path":"kv_quant/evaluation_gsm8k.py","file_url":"https://github.com/georgia-tech-synergy-lab/microscopiq-llm-quantization/blob/HEAD/kv_quant/evaluation_gsm8k.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6065f749757a201"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}