{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KCRU7TYZSHBOFDOHIYB74RMM5E","short_pith_number":"pith:KCRU7TYZ","schema_version":"1.0","canonical_sha256":"50a34fcf1991c2e28dc74603fe458ce90fbb394a604a1a63b5a39ad28dfaed34","source":{"kind":"arxiv","id":"2605.13915","version":1},"attestation_state":"computed","paper":{"title":"Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Decomposing BF16 activations into low-precision scales lets quantized weights multiply directly via native GEMM.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengqiu Hu, Fangzheng Miao, Jun Li, Junyi Fan, Lingchao Zheng, Qichen Liao, Rui Shi, Yuwei Fan","submitted_at":"2026-05-13T09:49:56Z","abstract_excerpt":"Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplication has become a critical bottleneck on modern AI accelerators. On architectures with decoupled compute units (e.g., Ascend NPUs), dequantization operations can consume more cycles than the matrix multiplication itself, leaving the high-throughput tensor cores underutilized. This paper presents Multi-Scale Dequant (MSD), a quantization framework that removes weight/KV dequantization from the GEMM critical path. Instead"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-13T09:49:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"07c5f209588171790c38ceed67b05b60fde9b7ca4dc7724170c0db4ee2f5a181","abstract_canon_sha256":"ab7b7c8573619592f3a7b9ec9deb8268e5e2cf91535a29a1df75056ca742f810"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:18.764477Z","signature_b64":"/SZgaWUJX6aMA8GuDOyZPjntzSsnfoZbXR8BRLjjBnJPN2bJuTCtnLhgDBKqk8NdjXUXI3VwGeaIBFms8fmvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50a34fcf1991c2e28dc74603fe458ce90fbb394a604a1a63b5a39ad28dfaed34","last_reissued_at":"2026-05-17T23:39:18.763747Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:18.763747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Decomposing BF16 activations into low-precision scales lets quantized weights multiply directly via native GEMM.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengqiu Hu, Fangzheng Miao, Jun Li, Junyi Fan, Lingchao Zheng, Qichen Liao, Rui Shi, Yuwei Fan","submitted_at":"2026-05-13T09:49:56Z","abstract_excerpt":"Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-precision for matrix multiplication has become a critical bottleneck on modern AI accelerators. On architectures with decoupled compute units (e.g., Ascend NPUs), dequantization operations can consume more cycles than the matrix multiplication itself, leaving the high-throughput tensor cores underutilized. This paper presents Multi-Scale Dequant (MSD), a quantization framework that removes weight/KV dequantization from the GEMM critical path. Instead"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"For INT8 weights (W4A16), two-pass INT8 decomposition achieves near 16 effective bits. For MXFP4 weights (W4A16), two-pass MXFP4 decomposition yields near 6.6 effective bits with error bound 1/64 per block surpassing single-pass MXFP8 while maintaining the same effective GEMM compute time.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the multi-scale activation decomposition can be implemented with native hardware-accelerated GEMM without introducing pipeline stalls or accuracy loss beyond the derived bounds, and that the closed-form latency models accurately predict real hardware behavior.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MSD eliminates dequantization from the GEMM path by decomposing BF16 activations into multiple low-precision parts that multiply directly with INT8 or MXFP4 weights, achieving near-16 effective bits for INT8 and 6.6 for MXFP4 with reduced HBM traffic.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Decomposing BF16 activations into low-precision scales lets quantized weights multiply directly via native GEMM.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1c51d3ec24f85f8de4ab16604dd1578181b630d655d0ed344186bf5547b845af"},"source":{"id":"2605.13915","kind":"arxiv","version":1},"verdict":{"id":"4b1150f9-d12f-4da5-a483-457377a4b710","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:53:49.087136Z","strongest_claim":"For INT8 weights (W4A16), two-pass INT8 decomposition achieves near 16 effective bits. For MXFP4 weights (W4A16), two-pass MXFP4 decomposition yields near 6.6 effective bits with error bound 1/64 per block surpassing single-pass MXFP8 while maintaining the same effective GEMM compute time.","one_line_summary":"MSD eliminates dequantization from the GEMM path by decomposing BF16 activations into multiple low-precision parts that multiply directly with INT8 or MXFP4 weights, achieving near-16 effective bits for INT8 and 6.6 for MXFP4 with reduced HBM traffic.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the multi-scale activation decomposition can be implemented with native hardware-accelerated GEMM without introducing pipeline stalls or accuracy loss beyond the derived bounds, and that the closed-form latency models accurately predict real hardware behavior.","pith_extraction_headline":"Decomposing BF16 activations into low-precision scales lets quantized weights multiply directly via native GEMM."},"references":{"count":30,"sample":[{"doi":"","year":2024,"title":"DeepSeek.FlashMLA: Efficient MLA for Large Language Models. Technical Report, 2024. https://github.com/deepseek-ai/FlashMLA","work_id":"93f944c5-ef20-4968-bded-2807bc81f255","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Technical Blog, 2025.https://github.com/deepseek-ai/FlashMLA/blob/main/docs/ 20250929-hopper-fp8-sparse-deep-dive.md","work_id":"ab768edf-a287-47b5-ac22-b0b99458446e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","work_id":"19ed8c44-202a-48f6-8169-637d5a5f2408","ref_index":3,"cited_arxiv_id":"2210.17323","is_internal_anchor":true},{"doi":"","year":2023,"title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","work_id":"ea9d1d72-db24-4cae-8c89-4ecd83dd87c1","ref_index":4,"cited_arxiv_id":"2306.00978","is_internal_anchor":true},{"doi":"","year":2024,"title":"Castro, Jiale Chen, Torsten Hoefler, and Dan Alistarh","work_id":"19ce2d31-0683-4f81-9db6-b9ca47099921","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":30,"snapshot_sha256":"d39d51c469102fe8b184d2fbc89ed7dc8b3818489b20245e2d902f7caf5c1e76","internal_anchors":6},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.13915","created_at":"2026-05-17T23:39:18.763870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13915v1","created_at":"2026-05-17T23:39:18.763870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13915","created_at":"2026-05-17T23:39:18.763870+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCRU7TYZSHBO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCRU7TYZSHBOFDOH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCRU7TYZ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCRU7TYZSHBOFDOHIYB74RMM5E","json":"https://pith.science/pith/KCRU7TYZSHBOFDOHIYB74RMM5E.json","graph_json":"https://pith.science/api/pith-number/KCRU7TYZSHBOFDOHIYB74RMM5E/graph.json","events_json":"https://pith.science/api/pith-number/KCRU7TYZSHBOFDOHIYB74RMM5E/events.json","paper":"https://pith.science/paper/KCRU7TYZ"},"agent_actions":{"view_html":"https://pith.science/pith/KCRU7TYZSHBOFDOHIYB74RMM5E","download_json":"https://pith.science/pith/KCRU7TYZSHBOFDOHIYB74RMM5E.json","view_paper":"https://pith.science/paper/KCRU7TYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13915&json=true","fetch_graph":"https://pith.science/api/pith-number/KCRU7TYZSHBOFDOHIYB74RMM5E/graph.json","fetch_events":"https://pith.science/api/pith-number/KCRU7TYZSHBOFDOHIYB74RMM5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCRU7TYZSHBOFDOHIYB74RMM5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCRU7TYZSHBOFDOHIYB74RMM5E/action/storage_attestation","attest_author":"https://pith.science/pith/KCRU7TYZSHBOFDOHIYB74RMM5E/action/author_attestation","sign_citation":"https://pith.science/pith/KCRU7TYZSHBOFDOHIYB74RMM5E/action/citation_signature","submit_replication":"https://pith.science/pith/KCRU7TYZSHBOFDOHIYB74RMM5E/action/replication_record"}},"created_at":"2026-05-17T23:39:18.763870+00:00","updated_at":"2026-05-17T23:39:18.763870+00:00"}