BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration | Paper Citation Record

Observation 5980f8c2-9ac9-4b74-8e65-5e0c6bca93cd · outbound

This paper cites 01-ai/yi-6b.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration 01-ai/yi-6b

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:07.093803Z

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 f3db5b81-78fd-46ec-817c-fb981a9bd287 · outbound

This paper cites BitMoD Artifacts,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration BitMoD Artifacts,

Reference 2

Resolution: verified exact; doi, observed 2026-08-12T18:18:05.748429Z

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 85c2b403-7f55-4119-9554-9a3dc3c2039f · outbound

This paper cites Bit-pragmatic deep neural network computing,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Bit-pragmatic deep neural network computing,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:07.078440Z

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 b1d1d050-6357-4e44-a76b-6576bf2429e7 · outbound

This paper cites QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.277708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 283835d1-d567-4638-a37d-c325ce5fac9f · outbound

This paper cites FPRaker: A process- ing element for accelerating neural network training,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration FPRaker: A process- ing element for accelerating neural network training,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:07.063442Z

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 1ab82118-8b93-4fd4-b0b9-4639df009127 · outbound

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

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration CACTI 7: New tools for interconnect exploration in innovative off-chip memories,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:07.048207Z

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 8247cbb4-f2c7-479e-af6c-7e86b6ba2857 · outbound

This paper cites PIQA: Reasoning about Physical Commonsense in Natural Language.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration PIQA: Reasoning about Physical Commonsense in Natural Language

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.295419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bb55cd6-20b9-410b-85a1-fc2509bf2904 · outbound

This paper cites A signed binary multiplication technique,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration A signed binary multiplication technique,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:07.032222Z

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 e693a695-8dfa-455c-96f3-26882d34f732 · outbound

This paper cites Language Models are Few-Shot Learners,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Language Models are Few-Shot Learners,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:07.016246Z

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 c8357a80-ce17-4376-8e94-8a10bda052d8 · outbound

This paper cites QuIP: 2-Bit Quantization of Large Language Models With Guarantees.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration QuIP: 2-Bit Quantization of Large Language Models With Guarantees

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.311475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 479af3e7-051c-426f-9b63-c405f4b01b9a · outbound

This paper cites EfficientQAT: Efficient Quantization-Aware Training for Large Language Models.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.317424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dccfd08-f436-4a41-9d2f-7da58dade405 · outbound

This paper cites BBS: Bi-directional bit-level sparsity for deep learning acceleration,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration BBS: Bi-directional bit-level sparsity for deep learning acceleration,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:07.001260Z

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 cee050f3-4088-47be-b257-5ebbad780cd2 · outbound

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

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.334165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dd416d3-fa3a-4749-bfbb-8be9bd237287 · outbound

This paper cites VS-Quant: Per-vector scaled quantization for accurate low-precision neural network inference,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration VS-Quant: Per-vector scaled quantization for accurate low-precision neural network inference,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.985768Z

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 3ee0bdbf-5c80-4a4f-a57f-37e70919a3b5 · outbound

This paper cites LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.345398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d175240-32ff-4a1c-b08a-03049c74372f · outbound

This paper cites 8-bit Optimizers via Block-wise Quantization.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration 8-bit Optimizers via Block-wise Quantization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.352436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5de9375-3bab-4329-9031-273fd6e52c1e · outbound

This paper cites QLoRA: Efficient Finetuning of Quantized LLMs.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration QLoRA: Efficient Finetuning of Quantized LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.360468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8db960d5-1417-4ef1-adb4-636f12b28563 · outbound

This paper cites Documenting large webtext corpora: A case study on the colossal clean crawled corpus,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Documenting large webtext corpora: A case study on the colossal clean crawled corpus,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.971045Z

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 b6cda7ca-1185-4e43-876d-878d71f5eb86 · outbound

This paper cites Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.378635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3545e30f-95d4-4a26-bbc4-f21d6b72dc04 · outbound

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

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.384374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddfe7364-2d0d-436f-ab60-51c3a907f32d · outbound

This paper cites A framework for few-shot language model evaluation,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration A framework for few-shot language model evaluation,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.955989Z

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 be480d8e-aee2-44cd-b3a2-f461bf46836d · outbound

This paper cites Ai and memory wall,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Ai and memory wall,

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.403258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a69e1c-d141-402f-b7f2-99c277903d3e · outbound

This paper cites SparTen: A sparse tensor accelerator for convolutional neural net- works,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration SparTen: A sparse tensor accelerator for convolutional neural net- works,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.929217Z

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 0d38f1b3-3691-420e-aee0-19b0f326cda5 · outbound

This paper cites Eureka: Efficient tensor cores for one-sided unstructured sparsity in dnn inference,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Eureka: Efficient tensor cores for one-sided unstructured sparsity in dnn inference,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.914369Z

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 e73d0ec0-f500-4865-9674-ce9d76d013be · outbound

This paper cites OliVe: Accelerating large language models via hardware-friendly outlier-victim pair quantization,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration OliVe: Accelerating large language models via hardware-friendly outlier-victim pair quantization,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.899467Z

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 f5e1e0db-32d5-40fd-b2f0-64bbb5dd0d49 · outbound

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

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration ANT: Exploiting adaptive numerical data type for low-bit deep neural network quantization,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.883982Z

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 ee59c750-11f7-459f-9815-ebfb865b8435 · outbound

This paper cites FIGNA: Integer unit-based accelerator design for fp-int gemm preserving numerical accuracy,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration FIGNA: Integer unit-based accelerator design for fp-int gemm preserving numerical accuracy,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.433723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a54e312-1d68-430f-975c-db83cf9d2b67 · outbound

This paper cites Stripes: Bit-serial deep neural network computing,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Stripes: Bit-serial deep neural network computing,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.857184Z

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 c003ceb1-e834-4fa9-a93f-2963c7bb798f · outbound

This paper cites DRAMsim3: A cycle-accurate, thermal-capable dram simulator,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration DRAMsim3: A cycle-accurate, thermal-capable dram simulator,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.841526Z

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 c7bfffa2-5e67-44db-af87-c87d603e6992 · outbound

This paper cites AWQ: Activation-aware weight quanti- zation for llm compression and acceleration,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration AWQ: Activation-aware weight quanti- zation for llm compression and acceleration,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.826244Z

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 d62349f3-65fb-469f-a062-cce71e198d54 · outbound

This paper cites LLM-QAT: Data-Free Quantization Aware Training for Large Language Models.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.459059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5a1814d-ea1c-46dd-a8c9-d88538f1ba26 · outbound

This paper cites Torch2Chip: An end-to-end customizable deep neural network compression and deployment toolkit for prototype hardware accelerator design,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Torch2Chip: An end-to-end customizable deep neural network compression and deployment toolkit for prototype hardware accelerator design,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.812130Z

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 5b3eedc9-d35b-4eb3-b600-5fc5a3d69f79 · outbound

This paper cites Pointer Sentinel Mixture Models.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Pointer Sentinel Mixture Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.469720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81d9296d-5f45-4c8d-863f-3f33405fbfd7 · outbound

This paper cites Meta llama.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Meta llama

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.797973Z

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 16847e1a-113b-4511-9d86-e791d99069ae · outbound

This paper cites Meta llama 3.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Meta llama 3

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.782651Z

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 403f10ea-6298-4d20-b183-be7cc6748a9a · outbound

This paper cites microsoft/phi-2.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration microsoft/phi-2

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.767329Z

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 b725fec7-f52c-423a-8b77-a3f1e5b557ea · outbound

This paper cites Jetson TX2 Module.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Jetson TX2 Module

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.752027Z

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 c80b6c48-46be-4ec0-a7e5-2730e6c31b47 · outbound

This paper cites OCP Microscaling Formats (MX) Specification.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration OCP Microscaling Formats (MX) Specification

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.736192Z

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 c30a3d7d-d8fc-43e4-9b0b-ef928c26f6e8 · outbound

This paper cites Energy-efficient neural network accel- erator based on outlier-aware low-precision computation,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Energy-efficient neural network accel- erator based on outlier-aware low-precision computation,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.721280Z

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 517ccf45-9858-4d36-b639-26515244142c · outbound

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

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration With shared microexponents, a little shifting goes a long way,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.706445Z

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 2e0409e3-f551-44da-b734-00bd9a9c074b · outbound

This paper cites WinoGrande: An Adversarial Winograd Schema Challenge at Scale.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.513379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a457cf58-7723-45a9-9ada-8dc7e4b8e1bc · outbound

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

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.519077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a532866-447d-4e22-a875-5c451cf1c976 · outbound

This paper cites Laconic deep learning inference acceleration,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Laconic deep learning inference acceleration,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.691090Z

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 75846753-f325-412f-be10-30a2118b1a66 · outbound

This paper cites FlexGen: High-throughput generative inference of large language models with a single gpu,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration FlexGen: High-throughput generative inference of large language models with a single gpu,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.675090Z

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 ced9e45b-9af1-4385-b3fd-e58832ef088a · outbound

This paper cites BitWave: Exploiting column-based bit-level sparsity for deep learning accelera- tion,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration BitWave: Exploiting column-based bit-level sparsity for deep learning accelera- tion,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.658690Z

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 c2cd6ec7-6458-40c1-a668-fbba858da6da · outbound

This paper cites Recursive deep models for semantic compositionality over a sentiment treebank,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Recursive deep models for semantic compositionality over a sentiment treebank,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.642088Z

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 5745f5c3-a3f5-44d5-869b-5d1251baba60 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration LLaMA: Open and Efficient Foundation Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.544497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ded4225a-9a55-406d-a7e9-75474353d037 · outbound

This paper cites Dual-side sparse tensor core,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Dual-side sparse tensor core,

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.625619Z

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 ba4a69c7-6dba-4c8d-8c65-c2e4ab1dcced · outbound

This paper cites ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.554103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6794c968-4311-451b-82f0-869deebffd6e · outbound

This paper cites HighLight: Efficient and flexible dnn acceleration with hierar- chical structured sparsity,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration HighLight: Efficient and flexible dnn acceleration with hierar- chical structured sparsity,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.609183Z

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 81bf2abb-2e50-4d24-94fe-15fb05766beb · outbound

This paper cites Quant-llm: Accelerating the serving of large language models via fp6- centric algorithm-system co-design on modern gpus,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Quant-llm: Accelerating the serving of large language models via fp6- centric algorithm-system co-design on modern gpus,

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.592575Z

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 e1de944c-da81-4f81-af23-5ee1f9ed88ae · outbound

This paper cites SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.569895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 405b02e5-3090-4efd-b4dc-2c5bd61b737b · outbound

This paper cites ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.575588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 606dc756-95a5-425d-9d03-5d5496ea83f8 · outbound

This paper cites GOBO: Quantizing attention-based nlp models for low latency and energy efficient inference,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration GOBO: Quantizing attention-based nlp models for low latency and energy efficient inference,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.576515Z

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 5148d089-888a-4569-a368-292371c62538 · outbound

This paper cites Mokey: enabling narrow fixed-point inference for out-of-the-box floating-point transformer models,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Mokey: enabling narrow fixed-point inference for out-of-the-box floating-point transformer models,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.560040Z

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 a8477de0-8536-4c58-b2bc-256281b524e6 · outbound

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

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration HellaSwag: Can a machine really finish your sentence?

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.544396Z

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 6d2025b9-d479-43f7-a13b-0019896050f4 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration OPT: Open Pre-trained Transformer Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.596760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7071b34d-afad-42e3-8527-b25bc1cc1da9 · outbound

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

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Atom: Low-bit quantization for efficient and accurate llm serving,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.529242Z

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 3303371c-20b0-4fce-abae-616bb3a6d52b · outbound

This paper cites Cambricon-S: Addressing irregularity in sparse neural networks through a cooperative software/hardware approach,.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Cambricon-S: Addressing irregularity in sparse neural networks through a cooperative software/hardware approach,

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.607280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36f6281a-0d00-4f7d-901a-4a42eb74069e · outbound

This paper cites an unresolved cited work.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-12T18:18:06.503921Z

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 78bb736f-fabf-47bd-b937-bd5f66bcb390 · outbound

This paper cites an unresolved cited work.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-12T18:18:06.489162Z

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 b7bc8668-c63e-4388-8e12-71a83e1db210 · outbound

This paper cites The quantization experiments require CUDA.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration The quantization experiments require CUDA

Reference 63

Resolution: verified exact; raw_fallback, observed 2026-08-12T18:18:05.847885Z

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 7ef2cb9f-aa8c-4bd1-9b74-f3a7bf0e05f9 · outbound

This paper cites This can reproduce the results in Table VI and Table VIII.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration This can reproduce the results in Table VI and Table VIII

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.472199Z

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 4fda59cd-4fda-4ed0-83ef-5322340e1d73 · outbound

This paper cites This can reproduce the results in Fig.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration This can reproduce the results in Fig

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.455376Z

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 ccab6954-7b06-4598-a270-b80f437b9928 · outbound

This paper cites This can reproduce the AWQ results in Table XI.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration This can reproduce the AWQ results in Table XI

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.439448Z

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 04b6b87e-c3f0-4157-a89b-5fbe856fd78c · outbound

This paper cites This can reproduce the OmniQuant results in Table XI.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration This can reproduce the OmniQuant results in Table XI

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.423721Z

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 c92366f4-f3f2-4e23-92e4-787655a12532 · outbound

This paper cites This can reproduce the results in Table XII.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration This can reproduce the results in Table XII

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.408812Z

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 4507a61e-6769-434b-bce8-d90d75325cd4 · outbound

This paper cites $ cd bitmod quant $ conda activate awq−bitmod In ‘ run_exp.sh’, modify the ‘ export’ command by specifying the HuggingFace home directory, ‘ HF_HOME’, on your computer.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration $ cd bitmod quant $ conda activate awq−bitmod In ‘ run_exp.sh’, modify the ‘ export’ command by specifying the HuggingFace home directory, ‘ HF_HOME’, on your computer

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.392812Z

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 b335f717-f077-4227-9607-3bc27e81bae1 · outbound

This paper cites When enabled / disabled, it will evaluate the hardware performance of generative / discriminative tasks.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration When enabled / disabled, it will evaluate the hardware performance of generative / discriminative tasks

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.377663Z

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 6a3efef1-2698-4d18-842d-329571d40167 · outbound

This paper cites You can compare these with the AWQ results in Table XI.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration You can compare these with the AWQ results in Table XI

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.362976Z

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 4a30bf33-4317-4d58-adb4-51ffd951a815 · outbound

This paper cites an unresolved cited work.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-12T18:18:06.347977Z

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 607bbf41-894b-4510-b912-b78731f0a07c · outbound

This paper cites You can compare these results with the SmoothQuant results in Table XII.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration You can compare these results with the SmoothQuant results in Table XII

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.331716Z

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 28788e20-1a97-4a3f-8bcd-8009204c5ae3 · outbound

This paper cites an unresolved cited work.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-12T18:18:06.314620Z

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 38334d65-423d-4216-acd0-2b1ac721a5f5 · outbound

This paper cites 7 and Fig.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration 7 and Fig

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:18:06.297037Z

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 8da12c5d-9ead-487d-a3d2-5fd3b0df19fa · outbound

This paper cites an unresolved cited work.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-12T18:18:06.280993Z

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 97cd8206-4895-4bee-9b4d-ff9670629902 · outbound

This paper cites an unresolved cited work.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-08-12T18:18:06.265003Z

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 9b868ba6-42a4-4fa5-91b8-220b93c04e97 · outbound

This paper cites an unresolved cited work.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-12T18:18:06.250285Z

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 44b1c974-e20b-4d19-8cc4-f47a8ac52edb · outbound

This paper cites Available: https://zenodo.org/records/10256836.

BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration Available: https://zenodo.org/records/10256836

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-12T18:18:05.398440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers