Paper Citation Record · LEDGER

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving

As of 15 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 2 inbound Pith citation observations for arXiv:2509.01229.

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

pith.paper-citation-record.v1
2509.01229 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T12:51:01.240091Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T12:38:31.783807Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T12:41:22.816856Z

Reference resolution

37 of 37 outbound references displayed

verified exact2
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 33d69fc8-5ca4-482c-8991-68d8b707075c · outbound

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

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:58.727339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36a89caf-b328-4462-9615-5b9d20f67e4c · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-05T12:51:01.804292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 866efa00-67b3-4e79-9ef7-4b994c45f1be · outbound

This paper cites Low-Rank Quantization-Aware Training for LLMs.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Low-Rank Quantization-Aware Training for LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:59.043745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c4bb3cb-8bb4-4c7c-9d5e-ead0b2eef072 · outbound

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

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:59.236249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cda9b768-4f76-48e3-9f42-ba2f16c6e77e · outbound

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

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:59.329622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f424dd9e-3948-4a54-9a70-5e333c78988d · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:59.389003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab9adc55-311a-4df8-b4e0-92636de41a5c · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-05T12:51:01.790186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2b4168fd-093a-4644-a754-43deece68509 · outbound

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

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:59.565844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26d02f9d-50c9-4cad-abeb-719682daf6ff · outbound

This paper cites The Llama 3 Herd of Models.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving The Llama 3 Herd of Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:59.639928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab963050-78d5-4e73-b9b2-da5785f3f1da · outbound

This paper cites Mistral 7B.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Mistral 7B

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:59.710091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8961faf1-5dfd-496a-aa6c-8be7e5f45def · outbound

This paper cites Mixtral of Experts.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Mixtral of Experts

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:59.789990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e5cd3d2-23aa-4f5c-98a8-c68ab9b78c3d · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T12:50:59.871156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb58c9ee-55a7-4e39-b26f-664f097f45a3 · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-05T12:51:01.766163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dd669daa-669b-4d2e-999d-a92959458e57 · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-05T12:51:01.752455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 28a5a33a-5a88-4d97-acff-9206d9d920fd · outbound

This paper cites QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:00.115901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16d86e1e-37b1-41af-baf9-37c7abe3fa62 · outbound

This paper cites COMET: Towards Partical W4A4KV4 LLMs Serving.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving COMET: Towards Partical W4A4KV4 LLMs Serving

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-05T12:51:01.499545Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bbe18e3d-6411-4361-856c-30c03ce71e59 · outbound

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

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:00.337520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f33c51b6-621f-4308-85da-6c2360e1cdaa · outbound

This paper cites SpinQuant: LLM quantization with learned rotations.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving SpinQuant: LLM quantization with learned rotations

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:00.448570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2f26be9-8d3d-4e3e-b6aa-fdcca2ba7596 · outbound

This paper cites Pointer Sentinel Mixture Models.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Pointer Sentinel Mixture Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:00.524851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647173bf-de49-49d0-98b8-bdd9b4e5e82f · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-05T12:51:01.738910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d30b226d-8ee0-4c29-991d-e5be8695c406 · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:00.710364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 722f42d6-ee3f-4cd1-b8bc-b777d2f32e5d · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-05T12:51:01.715591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 23d72f5b-203a-437d-b972-e538b94b3b7c · outbound

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

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:00.895682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 821ad1a4-168c-4ef8-900d-89c007ed6c61 · outbound

This paper cites Squat: Quant Small Language Models on the Edge.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Squat: Quant Small Language Models on the Edge

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-05T12:51:01.418595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 095fda24-251a-40d6-874d-3d58dca313f3 · outbound

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

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving LLaMA: Open and Efficient Foundation Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.077785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16b23d92-a37b-439a-b139-dd9610cfdf59 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.158011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f68407fc-0970-4982-8aff-875ce0a25f00 · outbound

This paper cites BitNet: Scaling 1-bit Transformers for Large Language Models.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving BitNet: Scaling 1-bit Transformers for Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.198277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 057bd4f2-a8c0-4035-9284-998b1ad53b9a · outbound

This paper cites Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.202661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e22a4f09-6b85-47ab-8808-4fe552f61a7b · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.207097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca793098-5702-4d56-9da1-abd372637612 · outbound

This paper cites OneBit: Towards Extremely Low-bit Large Language Models.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving OneBit: Towards Extremely Low-bit Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.211009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bfdf7f1-8425-4bf5-bb83-577889c2d4be · outbound

This paper cites Yi: Open Foundation Models by 01.AI.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Yi: Open Foundation Models by 01.AI

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.215194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a0e2c2e-003c-44b8-bea8-7160c5f5309f · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-05T12:51:01.691688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 916dd6c4-d250-4e2a-9174-e4c7c035e62c · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.223251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49c6fe9f-3712-4dab-becc-206455f21cbc · outbound

This paper cites QQQ: Quality Quattuor-Bit Quantization for Large Language Models.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving QQQ: Quality Quattuor-Bit Quantization for Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.231907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74c042ce-ba89-427b-a4d8-66b5bd8a9d7a · outbound

This paper cites an unresolved cited work.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-05T12:51:01.667807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 905c8c31-43ef-4744-a325-f3a148f02657 · outbound

This paper cites DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.240091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e1da5af-0771-4817-955d-d6ae33c03305 · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-05T12:51:01.227376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 70332ef3-f172-4b80-a889-757a0a393ff8 · inbound

LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers cites this paper.

LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:41:22.819166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e57b1a6c-4eb1-4c46-aff3-a37ea38ccb25 · inbound

Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference cites this paper.

Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T02:58:34.214757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.