Paper Citation Record · LEDGER

FP4 All the Way: Fully Quantized Training of LLMs

As of 14 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 24 inbound Pith citation observations for arXiv:2505.19115.

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

pith.paper-citation-record.v1
2505.19115 v2

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:25:39.827829Z

measured 51 of 51 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 24 of 24 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T11:10:52.650817Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T12:59:52.409670Z

Reference resolution

27 of 27 outbound references displayed

verified exact0
verified fuzzy6
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6ba406ad-82b3-45e9-bc82-6741b521057b · outbound

This paper cites URL https://resources.nvidia.com/ en-us-blackwell-architecture.

FP4 All the Way: Fully Quantized Training of LLMs URL https://resources.nvidia.com/ en-us-blackwell-architecture

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:25:41.835562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4f76d78e-30d7-4b61-93db-f8e70456bda1 · outbound

This paper cites Language models are few-shot learners.

FP4 All the Way: Fully Quantized Training of LLMs Language models are few-shot learners

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:37.624166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13897263-99c9-41a4-b548-2c9e10523d40 · outbound

This paper cites Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs.

FP4 All the Way: Fully Quantized Training of LLMs Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:37.677654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68648de-15dd-4880-904d-14948d9d7bdb · outbound

This paper cites Accurate neural training with 4-bit matrix multiplications at standard formats.

FP4 All the Way: Fully Quantized Training of LLMs Accurate neural training with 4-bit matrix multiplications at standard formats

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:25:41.630104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b5e8933b-569f-4855-a39b-e475714a1e94 · outbound

This paper cites Redpajama: an open dataset for training large language models, 2023.

FP4 All the Way: Fully Quantized Training of LLMs Redpajama: an open dataset for training large language models, 2023

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:37.839077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28ca5bca-76b3-421a-ad43-ce8d50a21959 · outbound

This paper cites DeepSeek-V3 Technical Report.

FP4 All the Way: Fully Quantized Training of LLMs DeepSeek-V3 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:37.906504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d0176b9-a51c-4080-a674-fd9011da3652 · outbound

This paper cites QLoRA: Efficient Finetuning of Quantized LLMs.

FP4 All the Way: Fully Quantized Training of LLMs QLoRA: Efficient Finetuning of Quantized LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:37.978555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f59b69c3-0296-407c-b2e7-12e45dd8d740 · outbound

This paper cites Scaling FP8 training to trillion-token LLMs.

FP4 All the Way: Fully Quantized Training of LLMs Scaling FP8 training to trillion-token LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:38.069250Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7b9a476-e921-4eb2-a7ee-873421f5dc5b · outbound

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

FP4 All the Way: Fully Quantized Training of LLMs GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:38.148834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cbc7242-0508-417f-a06a-82983dde6859 · outbound

This paper cites Towards Automatic Concept-based Explanations.

FP4 All the Way: Fully Quantized Training of LLMs Towards Automatic Concept-based Explanations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:38.226601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f6e53c3-4769-4199-b206-286d11800f20 · outbound

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

FP4 All the Way: Fully Quantized Training of LLMs Awq: Activation-aware weight quantization for on-device llm compression and acceleration

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:25:41.407060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8d5d4d8a-3600-43c7-8af9-e07044b03515 · outbound

This paper cites QuEST: Stable Training of LLMs with 1-Bit Weights and Activations.

FP4 All the Way: Fully Quantized Training of LLMs QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:38.408806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cadca501-3ecf-453d-89b4-51f13c108a8d · outbound

This paper cites FP8-LM: Training FP8 Large Language Models.

FP4 All the Way: Fully Quantized Training of LLMs FP8-LM: Training FP8 Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:38.586190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ea209cf-3319-439a-9e0f-50606cd2b962 · outbound

This paper cites Nonlinear random matrix theory for deep learning.

FP4 All the Way: Fully Quantized Training of LLMs Nonlinear random matrix theory for deep learning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:25:41.030042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7b4d5fc0-00e7-4635-bd23-bcd65a4c4de4 · outbound

This paper cites Microscaling Data Formats for Deep Learning.

FP4 All the Way: Fully Quantized Training of LLMs Microscaling Data Formats for Deep Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:38.750726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 331594bd-b301-4f6c-8a28-039754152a95 · outbound

This paper cites Empirical Analysis of the Hessian of Over-Parametrized Neural Networks.

FP4 All the Way: Fully Quantized Training of LLMs Empirical Analysis of the Hessian of Over-Parametrized Neural Networks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:38.845174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fe26c97-1248-42e6-9e80-50d32788f270 · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.

FP4 All the Way: Fully Quantized Training of LLMs Roformer: Enhanced transformer with rotary position embedding

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:38.942131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5abf3f54-e5ea-4017-9b9b-51e609510ed1 · outbound

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

FP4 All the Way: Fully Quantized Training of LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:39.054033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30346e9c-fc01-46c8-b573-e6a49430264e · outbound

This paper cites Training LLMs with MXFP4.

FP4 All the Way: Fully Quantized Training of LLMs Training LLMs with MXFP4

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:39.162969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87270417-b027-4778-91be-96be6f139905 · outbound

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

FP4 All the Way: Fully Quantized Training of LLMs BitNet: Scaling 1-bit Transformers for Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:39.407120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2d37f27-6c2b-4f9a-8009-abfb75ab3631 · outbound

This paper cites an unresolved cited work.

FP4 All the Way: Fully Quantized Training of LLMs Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:25:40.851425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 476290e5-da91-4c8b-9712-a27c3547cc4f · outbound

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

FP4 All the Way: Fully Quantized Training of LLMs SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:39.599677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d81d5031-9355-4cbc-b0ec-e6d68c58ae2f · outbound

This paper cites Optimizing Large Language Model Training Using FP4 Quantization.

FP4 All the Way: Fully Quantized Training of LLMs Optimizing Large Language Model Training Using FP4 Quantization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:39.524611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 511862f2-1152-49b1-8f15-8a32debae8db · outbound

This paper cites Root mean square layer normalization.

FP4 All the Way: Fully Quantized Training of LLMs Root mean square layer normalization

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:25:40.481483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0ae21ed9-17b4-48d4-9155-936cc9b0febe · outbound

This paper cites useful descent.

FP4 All the Way: Fully Quantized Training of LLMs useful descent

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:25:40.278888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 01e5c2e3-bc79-4150-b62c-359f7c966eb5 · outbound

This paper cites an unresolved cited work.

FP4 All the Way: Fully Quantized Training of LLMs Unresolved cited work

Reference 2022

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:25:40.738238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7f3ac726-250d-44dd-82a3-daac1d91ea40 · outbound

This paper cites an unresolved cited work.

FP4 All the Way: Fully Quantized Training of LLMs Unresolved cited work

Reference 2025

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:25:41.141357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation dfb348c4-4296-4725-ae96-0980ae7a7fba · inbound

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

Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling FP4 All the Way: Fully Quantized Training of LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-17T02:23:52.818063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7fdd1f00-da0c-4bdf-bd18-6930aa9d5363 · inbound

BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models cites this paper.

BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models FP4 All the Way: Fully Quantized Training of LLMs

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-16T23:21:21.620411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 46960556-563e-4edb-8753-6880375aa4be · inbound

ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs cites this paper.

ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs FP4 All the Way: Fully Quantized Training of LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T11:10:52.650817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61097926-dfdd-4a4b-b540-c62ae915347a · inbound

High-Rate Quantized Matrix Multiplication I cites this paper.

High-Rate Quantized Matrix Multiplication I FP4 All the Way: Fully Quantized Training of LLMs

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-16T11:20:53.206184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1ded2507-6c15-48e0-9118-f3d4b0f3adf4 · inbound

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation cites this paper.

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation FP4 All the Way: Fully Quantized Training of LLMs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:53:15.750455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9936330a-b2b3-4187-a0f5-123894580e86 · inbound

LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM cites this paper.

LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIM FP4 All the Way: Fully Quantized Training of LLMs

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:15:49.608665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cf77dddc-4953-4186-bdba-5f030e14fe9f · inbound

HiFloat4 Format for Language Model Pre-training on Ascend NPUs cites this paper.

HiFloat4 Format for Language Model Pre-training on Ascend NPUs FP4 All the Way: Fully Quantized Training of LLMs

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:05:59.791732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cdd10c52-c1dd-4880-9f07-684de0307828 · inbound

Pretraining large language models with MXFP4 on Native FP4 Hardware cites this paper.

Pretraining large language models with MXFP4 on Native FP4 Hardware FP4 All the Way: Fully Quantized Training of LLMs

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T05:41:26.391419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 29e2965f-27f3-4e26-9c0e-aa259043a244 · inbound

Pretraining large language models with MXFP4 on Native FP4 Hardware cites this paper.

Pretraining large language models with MXFP4 on Native FP4 Hardware FP4 All the Way: Fully Quantized Training of LLMs

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T21:19:28.705236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1ec88665-dc46-4b2c-8d80-b0108fcf52c6 · inbound

Pretraining large language models with MXFP4 on Native FP4 Hardware cites this paper.

Pretraining large language models with MXFP4 on Native FP4 Hardware FP4 All the Way: Fully Quantized Training of LLMs

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T05:19:46.442334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1267038f-a00a-49e0-a5b5-cfdd6ee773c3 · inbound

LoKA: Low-precision Kernel Applications for Recommendation Models At Scale cites this paper.

LoKA: Low-precision Kernel Applications for Recommendation Models At Scale FP4 All the Way: Fully Quantized Training of LLMs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:27.990594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0ab41feb-246c-44f7-88d0-4dd08e440945 · inbound

LoKA: Low-precision Kernel Applications for Recommendation Models At Scale cites this paper.

LoKA: Low-precision Kernel Applications for Recommendation Models At Scale FP4 All the Way: Fully Quantized Training of LLMs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-15T04:59:46.247998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a4359e84-ed0e-4b79-a928-c4d1a463401f · inbound

Grid Games: The Power of Multiple Grids for Quantizing Large Language Models cites this paper.

Grid Games: The Power of Multiple Grids for Quantizing Large Language Models FP4 All the Way: Fully Quantized Training of LLMs

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:47:26.495623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0a970008-0572-497b-b7fb-d116e17ce35b · inbound

Search Your Block Floating Point Scales! cites this paper.

Search Your Block Floating Point Scales! FP4 All the Way: Fully Quantized Training of LLMs

Reference 109

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:24.114030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e1798ca2-e196-49f9-a62b-e97776136ad9 · inbound

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation cites this paper.

LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation FP4 All the Way: Fully Quantized Training of LLMs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:03:13.286141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 08066668-74ff-4291-a7c5-ae89e48f4375 · inbound

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor cites this paper.

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor FP4 All the Way: Fully Quantized Training of LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:59:50.040245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 87a77ead-3487-4ab2-b95c-8e45c8563012 · inbound

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor cites this paper.

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor FP4 All the Way: Fully Quantized Training of LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:50:23.699203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0dc9c0c0-3f62-43fc-a49a-80d9f308bc8c · inbound

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor cites this paper.

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor FP4 All the Way: Fully Quantized Training of LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T18:04:57.963897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 85e19bbb-5c93-4ce5-a232-91a91599ee77 · inbound

ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention cites this paper.

ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention FP4 All the Way: Fully Quantized Training of LLMs

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:30:22.853160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 84eea01a-7c74-45e3-8444-e8d51f9d72a2 · inbound

Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation cites this paper.

Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation FP4 All the Way: Fully Quantized Training of LLMs

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-29T18:13:48.341253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4de64193-bee7-4a9f-803a-d7294170eab0 · inbound

SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference cites this paper.

SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference FP4 All the Way: Fully Quantized Training of LLMs

Reference 175

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T12:59:52.410951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5eedd8b1-b69f-4922-9e04-185ae5971f29 · inbound

Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention cites this paper.

Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention FP4 All the Way: Fully Quantized Training of LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T19:17:59.044982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29efcb24-d89d-486f-9773-2cb109c39845 · inbound

Stable FP4 Training via Transposition-Invariant Block Quantization cites this paper.

Stable FP4 Training via Transposition-Invariant Block Quantization FP4 All the Way: Fully Quantized Training of LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T05:04:00.326163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13cde71f-d6e9-4a27-a796-673ee2f73819 · inbound

GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference cites this paper.

GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference FP4 All the Way: Fully Quantized Training of LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T03:16:46.760453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.