Paper Citation Record · LEDGER

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition

As of 16 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2505.08981.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.08981 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:46:23.218413Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

21 of 21 outbound references displayed

verified exact2
verified fuzzy15
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation dbd54209-21f3-4fed-9405-838acd6c5b68 · outbound

This paper cites Rae, Oriol Vinyals, and Laurent Sifre.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Rae, Oriol Vinyals, and Laurent Sifre

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T21:46:23.118998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6beb585-68ae-4fd4-a4b5-558043069dde · outbound

This paper cites M4bram: Mixed-precision matrix-matrix multiplication in fpga block rams.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition M4bram: Mixed-precision matrix-matrix multiplication in fpga block rams

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.564892Z

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 b1d16bfc-9ecb-420f-b000-ed94bec445ba · outbound

This paper cites Msd: Mixing signed digit representations for hardware-efficient dnn acceleration on fpga with heterogeneous resources.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Msd: Mixing signed digit representations for hardware-efficient dnn acceleration on fpga with heterogeneous resources

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.549970Z

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 dee71ee8-47f8-45c7-afa4-e18926d0dec5 · outbound

This paper cites Democratizing neural ma- chine translation with OPUS-MT.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Democratizing neural ma- chine translation with OPUS-MT

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.534855Z

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 ad9b9f58-fb11-4ec6-9f3c-1c534041a094 · outbound

This paper cites Omniquant: Omnidirectionally calibrated quantization for large language models, 2024.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Omniquant: Omnidirectionally calibrated quantization for large language models, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T21:46:23.139139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3fff66a-3173-4584-9548-a39e5e29db75 · outbound

This paper cites Qllm: Accurate and efficient low-bitwidth quantization for large language models, 2024.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Qllm: Accurate and efficient low-bitwidth quantization for large language models, 2024

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.506708Z

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 6f3fc791-5796-4577-a26e-910f529db4d2 · outbound

This paper cites Efficient arbitrary precision acceleration for large language models on gpu tensor cores, 2024.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Efficient arbitrary precision acceleration for large language models on gpu tensor cores, 2024

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.489205Z

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 e4898226-3c6f-4410-be4d-42511c865935 · outbound

This paper cites Q8bert: Quantized 8bit bert.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Q8bert: Quantized 8bit bert

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.474136Z

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 aac596a7-35fc-41dd-b2d3-efa5553c8959 · outbound

This paper cites Q-bert: Hessian based ultra low precision quantization of bert.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Q-bert: Hessian based ultra low precision quantization of bert

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.458192Z

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 09eb866a-4af7-47ea-b2e4-40e00e3fa77b · outbound

This paper cites Owq: Outlier-aware weight quantization for efficient fine-tuning and inference of large language models.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Owq: Outlier-aware weight quantization for efficient fine-tuning and inference of large language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.443008Z

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 96c12863-bda7-490f-a7ff-1c3cdec005a2 · outbound

This paper cites Hawq: Hessian aware quantization of neural networks with mixed-precision.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Hawq: Hessian aware quantization of neural networks with mixed-precision

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T21:46:23.168431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4ac93e7-a401-4204-8c39-840f13031454 · outbound

This paper cites BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-15T21:46:23.285813Z

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 51426ebb-e62d-4c45-9137-6b920764db9b · outbound

This paper cites Optimizing bit-serial matrix multiplica- tion for reconfigurable computing.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Optimizing bit-serial matrix multiplica- tion for reconfigurable computing

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.415450Z

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 60f872e6-3a1f-403a-a971-02abb297cd71 · outbound

This paper cites Hihispmv: Sparse matrix vector multiplication with hierarchical row reductions on fpgas with high bandwidth memory.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Hihispmv: Sparse matrix vector multiplication with hierarchical row reductions on fpgas with high bandwidth memory

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.399802Z

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 ad0b3b13-9f5f-4fd5-97c6-07321e878da9 · outbound

This paper cites HASS: Hardware-Aware Sparsity Search for Dataflow DNN Accelerator.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition HASS: Hardware-Aware Sparsity Search for Dataflow DNN Accelerator

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-15T21:46:23.263510Z

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 90de80ed-2264-47ba-883d-ce89c42b9af4 · outbound

This paper cites Adaptable butterfly accelerator for attention-based nns via hardware and algorithm co-design.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Adaptable butterfly accelerator for attention-based nns via hardware and algorithm co-design

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.384463Z

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 275824aa-a5a4-4876-a287-29f5aae853ee · outbound

This paper cites Streamsvd: Low-rank ap- proximation and streaming accelerator co-design.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Streamsvd: Low-rank ap- proximation and streaming accelerator co-design

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.366096Z

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 f5ba8875-fc91-4098-973f-55f9f27a509d · outbound

This paper cites Charm: Composing heterogeneous accelerators for matrix multiply on versal acap architec- ture, 2023.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Charm: Composing heterogeneous accelerators for matrix multiply on versal acap architec- ture, 2023

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.349573Z

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 2473c3b1-39c4-4243-b2b9-d609f08395be · outbound

This paper cites Film-qnn: Efficient fpga acceleration of deep neural networks with intra-layer, mixed-precision quantization.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Film-qnn: Efficient fpga acceleration of deep neural networks with intra-layer, mixed-precision quantization

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.332969Z

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 3ebbecc7-6dbf-4877-ae6d-e4c0ae4d8643 · outbound

This paper cites Understanding the potential of fpga-based spatial acceleration for large language model inference.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Understanding the potential of fpga-based spatial acceleration for large language model inference

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:46:23.317160Z

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 1fe1fd53-c6bd-44b1-a568-66745d185d29 · outbound

This paper cites an unresolved cited work.

ITERA-LLM: Boosting Sub-8-Bit Large Language Model Inference via Iterative Tensor Decomposition Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:46:23.301735Z

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.

Pith citing papers

No inbound Pith citation observations are available.