Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference | Paper Citation Record

Observation c9c12499-2e2b-41b5-a52a-a149e625ea0b · outbound

This paper cites AMD Instinct™ MI350 Series GPUs,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference AMD Instinct™ MI350 Series GPUs,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.254496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 38f6080c-a363-4330-adc0-61b81412f0f8 · outbound

This paper cites System Card: Claude Opus 4 & Claude Sonnet 4,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference System Card: Claude Opus 4 & Claude Sonnet 4,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.245420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 83a2abac-bb0c-4fd5-a249-0cb396aaaee0 · outbound

This paper cites QuaRot: outlier-free 4-bit inference in rotated llms,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference QuaRot: outlier-free 4-bit inference in rotated llms,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.236474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 949f57d1-a545-4f46-8424-af02b4034e2e · outbound

This paper cites Cacti 7: New tools for interconnect exploration in innovative off-chip memories,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Cacti 7: New tools for interconnect exploration in innovative off-chip memories,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:28.263418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d98bff83-0c8f-406b-ba1f-0fbe50a22354 · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Piqa: Reasoning about physical commonsense in natural language,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.227307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8fc5a00d-0a28-4996-9cd6-cc39ec0b7450 · outbound

This paper cites Int v.s. fp: A comprehensive study of fine-grained low-bit quantization formats,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Int v.s. fp: A comprehensive study of fine-grained low-bit quantization formats,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:28.401800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c2c8913-fb8f-4491-af78-b5ec33739032 · outbound

This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:28.471068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48277872-e5ae-49e4-8e7e-4aab138abb8c · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:28.580769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9a7d5da-ac93-47c1-997c-294233991dce · outbound

This paper cites Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:28.676839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a83d7654-d208-40e5-858c-cd7b06bc6112 · outbound

This paper cites Efficient precision-scalable hardware for microscaling (mx) processing in robotics learning,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Efficient precision-scalable hardware for microscaling (mx) processing in robotics learning,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:28.699322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0573c81-314f-4b28-a94e-022414ad12b4 · outbound

This paper cites With shared microexponents, a little shifting goes a long way,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference With shared microexponents, a little shifting goes a long way,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:28.792184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 479b6f3c-623a-4d54-bc5a-2de962b1b321 · outbound

This paper cites Deepseek-v4: Towards highly efficient million-token context intelligence,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Deepseek-v4: Towards highly efficient million-token context intelligence,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:28.907764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b762538d-8fec-4633-999c-c990af96b4c5 · outbound

This paper cites LLM.int8(): 8-bit matrix multiplication for transformers at scale,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference LLM.int8(): 8-bit matrix multiplication for transformers at scale,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.212025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0d52327e-a994-4712-a432-e8aace3f64cc · outbound

This paper cites SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:29.065972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b83e9f0c-927d-4c3f-8660-7c00c0204d1c · outbound

This paper cites Extreme compression of large language models via additive quantization,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Extreme compression of large language models via additive quantization,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.202728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 35899f3b-85b2-4c86-97ea-076263ccede1 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:29.303924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf638634-a821-4b27-9813-0eabcd400783 · outbound

This paper cites The language model evaluation harness,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference The language model evaluation harness,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:29.417903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a8c3788-d6d7-416c-a0aa-37bb6bd0f321 · outbound

This paper cites Gemma 4 Model Overview,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Gemma 4 Model Overview,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.193835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e7b05792-47c7-4ea6-b42d-3ec3fdfafa03 · outbound

This paper cites ANT: Exploiting adaptive numerical data type for low-bit deep neural network quantization,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference ANT: Exploiting adaptive numerical data type for low-bit deep neural network quantization,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.184673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8029f34d-20a4-4469-bd82-df0ecdd958b5 · outbound

This paper cites BBAL: A bidirectional block floating point-based quantisation accelerator for large language models,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference BBAL: A bidirectional block floating point-based quantisation accelerator for large language models,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:29.770682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 125c4c63-2891-4ec1-a961-9cf9aef6f499 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Measuring Massive Multitask Language Understanding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:29.896018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f515fe-86d0-4f6a-870e-042bcc1a7de5 · outbound

This paper cites 1.1 computing’s energy problem (and what we can do about it),.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference 1.1 computing’s energy problem (and what we can do about it),

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.016464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17875c65-6793-40a3-bcbd-cb21bf5e4199 · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.113712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4770c4e1-84c9-40a2-820f-f86281e27bae · outbound

This paper cites M-ANT: Efficient low-bit group quantization for llms via mathematically adaptive numerical type,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference M-ANT: Efficient low-bit group quantization for llms via mathematically adaptive numerical type,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.169110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8a9df075-b593-4db8-b489-565517638e7b · outbound

This paper cites M2XFP: A metadata-augmented microscaling data format for efficient low-bit quantization,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference M2XFP: A metadata-augmented microscaling data format for efficient low-bit quantization,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.375670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c1f572b-6924-49b8-b55a-265e253bf2fd · outbound

This paper cites Blockdialect: block-wise fine-grained mixed format quantization for energy-efficient llm inference,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Blockdialect: block-wise fine-grained mixed format quantization for energy-efficient llm inference,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.158601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1942b81a-3f95-47fc-ac60-9edbe07e590e · outbound

This paper cites A diagram is worth a dozen images,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference A diagram is worth a dozen images,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.147849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5fb49d37-4664-4019-8491-513e06c21bb3 · outbound

This paper cites 14.2 a 16nm 216kb, 188.4tops/w and 133.5tflops/w microscaling multi- mode gain-cell cim macro edge-ai devices,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference 14.2 a 16nm 216kb, 188.4tops/w and 133.5tflops/w microscaling multi- mode gain-cell cim macro edge-ai devices,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.138096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9293ecb2-7281-40f4-9ea4-f69183e2d117 · outbound

This paper cites SqueezeLLM: dense-and-sparse quantiza- tion,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference SqueezeLLM: dense-and-sparse quantiza- tion,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.127987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1f446c27-ee3b-44c2-b0aa-87ce14dce278 · outbound

This paper cites Tender: Accelerating large language models via tensor decomposition and runtime requantization,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Tender: Accelerating large language models via tensor decomposition and runtime requantization,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.118081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 68b802df-f590-4a37-8d47-e15787d70166 · outbound

This paper cites MX+: Pushing the limits of microscaling formats for efficient large language model serving,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference MX+: Pushing the limits of microscaling formats for efficient large language model serving,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.808079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b42c4bc-c813-4322-9aeb-87e3d7147472 · outbound

This paper cites AWQ: Activation-aware weight quantization for on-device llm compression and acceleration,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference AWQ: Activation-aware weight quantization for on-device llm compression and acceleration,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.810712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d175522-191d-485b-864f-3e336d846344 · outbound

This paper cites Qserve: W4a8kv4 quantization and system co-design for efficient llm serving,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Qserve: W4a8kv4 quantization and system co-design for efficient llm serving,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.813720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe303a0a-7967-48ef-bba0-6916b10b4dd8 · outbound

This paper cites Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-05T10:54:31.243463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation da2dd973-057b-4547-84f8-d408236063a4 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Learn to explain: Multimodal reasoning via thought chains for science question answering,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.820251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbf06264-3899-4c5b-ba41-699d6a484938 · outbound

This paper cites Pointer sentinel mixture models,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Pointer sentinel mixture models,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.095906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ce95d21e-1406-4669-98a4-0523f4c90fca · outbound

This paper cites The Llama 3 Herd of Models.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference The Llama 3 Herd of Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.825891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28354834-da05-47a8-a1f2-f1e269bb85d5 · outbound

This paper cites Four MTIA Chips in Two Years: Scaling AI Experi- ences for Billions,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Four MTIA Chips in Two Years: Scaling AI Experi- ences for Billions,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.086557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4524645d-eafa-4379-bd0b-c0b96d1facf0 · outbound

This paper cites Recipes for Pre-training LLMs with MXFP8.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Recipes for Pre-training LLMs with MXFP8

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.832174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89dd0de1-3794-4a65-81dd-6b76de128c2f · outbound

This paper cites NVIDIA H100 Tensor Core GPU Datasheet,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference NVIDIA H100 Tensor Core GPU Datasheet,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.077146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ede43b36-648a-4bc5-8422-66a65e77d04c · outbound

This paper cites NVIDIA Blackwell Architecture Technical Brief,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference NVIDIA Blackwell Architecture Technical Brief,

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.058539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c378b2c6-7f03-425e-8096-0634641038ae · outbound

This paper cites OCP Microscaling Formats (MX) Specification,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference OCP Microscaling Formats (MX) Specification,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.048394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 96f60da0-4c40-4a88-a26d-c01fe9b2c159 · outbound

This paper cites OpenAI GPT-5 System Card,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference OpenAI GPT-5 System Card,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.037525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9235f464-15d1-4964-82b4-eab6716076e7 · outbound

This paper cites Paszke, S.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Paszke, S

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.850566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 026e5800-ad1d-4268-b9f8-e02e0ec0b35a · outbound

This paper cites Scale-sim v3: A modular cycle-accurate systolic accelerator simulator for end-to-end system analysis,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Scale-sim v3: A modular cycle-accurate systolic accelerator simulator for end-to-end system analysis,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.019795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6faf28f5-d8e9-49bf-8d03-f2d1878ab052 · outbound

This paper cites Microscopiq: Accelerating foundational models through outlier-aware microscaling quantization,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Microscopiq: Accelerating foundational models through outlier-aware microscaling quantization,

Reference 46

Resolution: metadata mismatch; raw_fallback, observed 2026-08-05T10:54:31.211877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 988dd783-6710-4168-9800-8fa23fba956c · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Gemma 2: Improving Open Language Models at a Practical Size

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.858903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d5b7539-4204-4fde-a6af-5cf1f3177c2b · outbound

This paper cites Pushing the limits of narrow precision inferencing at cloud scale with microsoft floating point,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Pushing the limits of narrow precision inferencing at cloud scale with microsoft floating point,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.008859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f8149f9c-a0c1-4b1e-84be-2c3e9c5b26d4 · outbound

This paper cites Microscaling Data Formats for Deep Learning.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Microscaling Data Formats for Deep Learning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.865642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1b68ba9-8e7e-4d30-9af9-23f8051ab664 · outbound

This paper cites Winogrande: an adversarial winograd schema challenge at scale,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Winogrande: an adversarial winograd schema challenge at scale,

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.869033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c3f1d7f-18c7-44ab-b77e-62787b4c2eaa · outbound

This paper cites OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.872438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c817380b-ca78-47b7-a649-d41cb3bb13ef · outbound

This paper cites Towards vqa models that can read,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Towards vqa models that can read,

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.998117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ea0eed34-34b1-4b9b-b1c9-15b74de6e25a · outbound

This paper cites Commonsenseqa: A question answering challenge targeting commonsense knowledge,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Commonsenseqa: A question answering challenge targeting commonsense knowledge,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.988088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 92f0e344-78fd-40aa-ac6a-384dabf9c983 · outbound

This paper cites A microscaling multi-mode gain-cell computing-in- memory macro for advanced ai edge device,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference A microscaling multi-mode gain-cell computing-in- memory macro for advanced ai edge device,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.977638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0f9c46a0-8a74-49b2-ad29-c854ada80fd8 · outbound

This paper cites Quip#: Even better llm quantization with hadamard incoherence and lattice codebooks,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Quip#: Even better llm quantization with hadamard incoherence and lattice codebooks,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.966233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c8c0dbc9-5fda-4415-a49b-b34e1914798e · outbound

This paper cites 30.1 a 28nm 127.54tflops/w mxfp6 and 117.42tflops/w mxfp8 compute-in-memory macro with adaptive- preserved-bit-width and serial-dual-bit-sliding schemes,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference 30.1 a 28nm 127.54tflops/w mxfp6 and 117.42tflops/w mxfp8 compute-in-memory macro with adaptive- preserved-bit-width and serial-dual-bit-sliding schemes,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.956423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e41a0196-9109-443b-97d9-14fa97783159 · outbound

This paper cites Accelergy: An architecture- level energy estimation methodology for accelerator designs,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Accelergy: An architecture- level energy estimation methodology for accelerator designs,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.894125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63e2bea2-e0a6-42cc-b28d-a2181327298e · outbound

This paper cites SmoothQuant: Accurate and efficient post-training quantization for large language models,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference SmoothQuant: Accurate and efficient post-training quantization for large language models,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.939793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 14e1b5ac-698f-466e-81f7-f6a81c81dbbc · outbound

This paper cites Inside Maia 100: Revolutionizing AI Workloads with Microsoft’s Custom AI Accelerator,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Inside Maia 100: Revolutionizing AI Workloads with Microsoft’s Custom AI Accelerator,

Reference 59

Resolution: verified exact; raw_fallback, observed 2026-08-05T10:54:31.096960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ce701b2b-ff15-4e2e-ac69-3e6a1a2eefa3 · outbound

This paper cites An empirical study of microscaling formats for low-precision llm training,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference An empirical study of microscaling formats for low-precision llm training,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.928622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a94af574-4fab-41b3-be30-29247e664c8b · outbound

This paper cites Qwen2.5 Technical Report.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Qwen2.5 Technical Report

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.904865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4480135-ffae-484b-a485-d5b94840eeef · outbound

This paper cites ZeroQuant: efficient and affordable post-training quantization for large- scale transformers,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference ZeroQuant: efficient and affordable post-training quantization for large- scale transformers,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.919045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c371b86c-9450-4eaa-aa06-56caf514d875 · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for expert agi,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.909352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a5732eb2-2ab1-4f99-a65c-9ab9668675d8 · outbound

This paper cites Hellaswag: Can a machine really finish your sentence?.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Hellaswag: Can a machine really finish your sentence?

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.899313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2fedea90-72f7-44d1-b563-6394105f8d4b · outbound

This paper cites Sageattention3: Microscaling fp4 attention for inference and an exploration of 8-bit training,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Sageattention3: Microscaling fp4 attention for inference and an exploration of 8-bit training,

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.916143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0425dbc-440e-4ee4-84bc-020d68b61a3d · outbound

This paper cites Atom: Low-bit quantization for efficient and accurate llm serving,.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Atom: Low-bit quantization for efficient and accurate llm serving,

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:31.889954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ebe5e4cd-69d1-4586-a98f-f71b09d188b4 · outbound

This paper cites CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-05T10:54:30.882544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d2a2b2c-93a8-4238-84da-dbd2ecbd8d5d · outbound

This paper cites Available: https://resources.nvidia.com/en-us-gpu- resources/h100-datasheet-24306.

Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference Available: https://resources.nvidia.com/en-us-gpu- resources/h100-datasheet-24306

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T10:54:32.068016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers