Corerope

Research library

The research, in full

Everything on this site is drawn from these files. They are the source of truth: the pages render them, and the charts are generated from them.
The survey

Stacked levers reach 1000x only against 2024

A roughly 1000x cut in cost and energy per solved task, at fixed quality, is credible against a 2024 baseline (a dense ~405B transformer in BF16 on H100s) but not, on current evidence, against the late-2026...

6,727 words · 01-report-path-to-1000x.md
The design

Corerope design: inventing a 1000x cheaper frontier LLM

Formerly titled "Thousandfold". Written Nov 19, 2026. Built on the companion report (01-report-path-to-1000x.md) and the experiments in /experiments.

3,935 words · 02-corerope-design.md
Research note

Low-bit numerics for LLM inference efficiency (quantization, QAT vs PTQ, pruning/N:M sparsity), state as of Nov 2026

Scope note: research done 2026-11-18. Dates are marked per finding. "Older" means pre-2025. Vendor claims are flagged as such. Several primary sources (BitNet b1.58 2B4T arXiv paper and HF model card) could not...

4,094 words · quantization_numerics.md
Research note

Sparse and Conditional Computation for LLM Inference Efficiency (MoE, activation sparsity, early exit, layer skipping, mixture-of-depths)

Research date: 2026-11-18. Older (pre-2025) results are marked [OLDER]. Some 2026 model specs come from secondary aggregators and are marked [SECONDARY].

2,916 words · moe_conditional_compute.md
Research note

Attention Alternatives and KV-Cache Efficiency for LLM Inference (state as of Nov 2026)

Notation: "[older]" marks pre-2025 results. "[not re-fetched]" marks well-known paper claims cited from the paper's abstract/arXiv record that were not re-opened during this research session (verify before...

3,038 words · attention_kv_cache.md
Research note

Decoding Efficiency and Test-Time Compute Economics (state as of Nov 2026)

Scope: speculative decoding (EAGLE-3, Medusa, draft models, lookahead), multi-token prediction (DeepSeek MTP and successors such as DSpark), diffusion LLMs (Mercury 1/2/2.5/3, Gemini Diffusion, DiffusionGemma,...

3,674 words · decoding_test_time.md
Research note

Capability Density, Distillation, and Inference Cost Trends for LLMs (as of Nov 2026)

Every major estimate puts the price decline at constant capability at roughly 5x to 40x per year, with the most recent and most careful estimate (Epoch, Sept 2026) at about 13x/year (47% per quarter) since...

3,317 words · distillation_cost_trends.md
Research note

Inference Hardware and Serving Systems: Energy and Cost per Token (state as of Nov 2026)

Notes on conventions: "Vendor claim" = stated by the company selling the hardware. "Independent" = SemiAnalysis InferenceX/InferenceMAX, EE Times hands-on demo, or academic measurement. "Audited" = MLPerf...

3,861 words · hardware_systems.md
Recorded results

Recorded experiment results (Nov 19, 2026)

338 words · RESULTS.md

Every source cited

130 distinct links from 62 sites, with each place they are cited. Labels in the notes say whether a figure was measured independently, claimed by a vendor, or derived.

  1. a16za16z.comCited in the survey line 23, distillation and cost trends line 33, distillation and cost trends line 34, distillation and cost trends line 35, distillation and cost trends line 129, distillation and cost trends line 146
  2. ACL Anthologyaclanthology.orgCited in distillation and cost trends line 107
  3. AI Weeklyaiweekly.coCited in the survey line 43, low-bit numerics line 25
  4. Alibaba Cloud / Qwen blogalibabacloud.comCited in attention and kv cache line 13, attention and kv cache line 92, attention and kv cache line 200
  5. AI2allenai.orgCited in the survey line 65, attention and kv cache line 99
  6. alphaXiv 2510.26692alphaxiv.orgCited in the survey line 65, attention and kv cache line 14, attention and kv cache line 94
  7. alphaXiv 2603.23701alphaxiv.orgCited in the survey line 55, moe and conditional compute line 127
  8. alphaXiv 2605.25745alphaxiv.orgCited in the survey line 77, decoding and test-time compute line 136
  9. alphaXiv 2605.26297alphaxiv.orgCited in the survey line 31, attention and kv cache line 135
  10. aman.aiaman.aiCited in the survey line 51, moe and conditional compute line 14, moe and conditional compute line 76, moe and conditional compute line 156
  11. AMD blogamd.comCited in low-bit numerics line 150
  12. Analytics India Magazineanalyticsindiamag.comCited in the survey line 69, decoding and test-time compute line 24
  13. Artificial Analysisartificialanalysis.aiCited in the survey line 75, decoding and test-time compute line 121, decoding and test-time compute line 166
  14. Artificial Analysisartificialanalysis.aiCited in the survey line 7, decoding and test-time compute line 122
  15. Artificial Analysisartificialanalysis.aiCited in the survey line 7, the survey line 59, distillation and cost trends line 78, distillation and cost trends line 79, distillation and cost trends line 80, distillation and cost trends line 81
  16. Artificial Analysisartificialanalysis.aiCited in the survey line 11, the survey line 51, moe and conditional compute line 13, moe and conditional compute line 79, moe and conditional compute line 141
  17. Artificial Analysisartificialanalysis.aiCited in the survey line 9, distillation and cost trends line 148
  18. arXiv 2312.04927arxiv.orgCited in attention and kv cache line 109
  19. arXiv 2402.01032arxiv.orgCited in attention and kv cache line 109
  20. Jamba paper (arXiv 2403.19887)arxiv.orgCited in attention and kv cache line 29
  21. DeepSeek-V2 paper (arXiv 2405.04434)arxiv.orgCited in attention and kv cache line 61, attention and kv cache line 168
  22. MagicDec arXiv 2408.11049arxiv.orgCited in decoding and test-time compute line 20
  23. arXiv 2408.14690arxiv.orgCited in the survey line 55, moe and conditional compute line 100
  24. DeepSeek-V3 tech reportarxiv.orgCited in decoding and test-time compute line 23
  25. arXiv 2502.05172arxiv.orgCited in moe and conditional compute line 35
  26. arXiv 2502.08606arxiv.orgCited in the survey line 59, distillation and cost trends line 106
  27. arXiv 2503.01840arxiv.orgCited in the survey line 69, decoding and test-time compute line 16
  28. arXiv 2504.01296arxiv.orgCited in the survey line 77, decoding and test-time compute line 132
  29. arXiv 2504.03624arxiv.orgCited in the survey line 65, attention and kv cache line 27, attention and kv cache line 100, attention and kv cache line 199
  30. Cartridgesarxiv.orgCited in the design line 128, the design line 195
  31. arXiv 2507.06457arxiv.orgCited in attention and kv cache line 91
  32. arXiv 2604.10852arxiv.orgCited in the survey line 87, hardware and serving line 38, hardware and serving line 97
  33. arXiv 2406.05955arxiv.orgCited in the survey line 55, moe and conditional compute line 101, moe and conditional compute line 108, moe and conditional compute line 166
  34. arXiv 2408.03314arxiv.orgCited in the survey line 77, decoding and test-time compute line 161
  35. arXiv 2410.06270arxiv.orgCited in moe and conditional compute line 158
  36. arXiv 2411.04330arxiv.orgCited in the survey line 45, low-bit numerics line 29, low-bit numerics line 30, low-bit numerics line 31, low-bit numerics line 92, low-bit numerics line 109, low-bit numerics line 110
  37. arXiv 2412.04315arxiv.orgCited in the survey line 23, the survey line 59, distillation and cost trends line 56, distillation and cost trends line 57, distillation and cost trends line 58, distillation and cost trends line 59, distillation and cost trends line 60, distillation and cost trends line 62, distillation and cost trends line 63, distillation and cost trends line 126
  38. TerEfficarxiv.orgCited in low-bit numerics line 68, low-bit numerics line 152
  39. arXiv 2507.17702arxiv.orgCited in the survey line 51, the survey line 170, moe and conditional compute line 34
  40. arXiv 2508.10925arxiv.orgCited in the survey line 51, moe and conditional compute line 22, moe and conditional compute line 78, moe and conditional compute line 154
  41. Diaz, 2025arxiv.orgCited in the design line 128
  42. arXiv 2509.25149arxiv.orgCited in the survey line 41, the survey line 170, low-bit numerics line 12, low-bit numerics line 13, low-bit numerics line 14, low-bit numerics line 15, low-bit numerics line 16, low-bit numerics line 63, low-bit numerics line 111, low-bit numerics line 149
  43. arXiv 2511.19495arxiv.orgCited in the survey line 59, distillation and cost trends line 124, distillation and cost trends line 125
  44. arXiv 2511.23455arxiv.orgCited in the survey line 23, distillation and cost trends line 18, distillation and cost trends line 19, distillation and cost trends line 20, distillation and cost trends line 21, distillation and cost trends line 22, distillation and cost trends line 23, distillation and cost trends line 24, distillation and cost trends line 25, distillation and cost trends line 26
  45. Nemotron 3 paper (arXiv 2512.20856)arxiv.orgCited in attention and kv cache line 28
  46. Engram paperarxiv.orgCited in the design line 42, the design line 193
  47. Mamba-3 paper (arXiv 2603.15569)arxiv.orgCited in attention and kv cache line 37
  48. arXiv 2310.02410arxiv.orgCited in moe and conditional compute line 164
  49. arXiv 2501.12948arxiv.orgCited in the survey line 59, distillation and cost trends line 83
  50. Stop Overthinking survey, arXiv 2503.16419arxiv.orgCited in decoding and test-time compute line 137, decoding and test-time compute line 138
  51. arXiv 2505.13417arxiv.orgCited in the survey line 77, decoding and test-time compute line 131
  52. Ling 2.0 paper, arXiv 2510.22115arxiv.orgCited in moe and conditional compute line 24, moe and conditional compute line 157
  53. search result: Kittyarxiv.orgCited in low-bit numerics line 93
  54. arXiv 2602.09113arxiv.orgCited in the survey line 69, decoding and test-time compute line 34
  55. arXiv PDFarxiv.orgCited in moe and conditional compute line 109
  56. arXiv 2606.02011arxiv.orgCited in the survey line 45, the survey line 47, low-bit numerics line 60, low-bit numerics line 90, low-bit numerics line 91, low-bit numerics line 92
  57. arXiv 2607.26515arxiv.orgCited in low-bit numerics line 153
  58. arXiv 2607.26571arxiv.orgCited in the survey line 9, the survey line 29, the design line 25, the design line 197, hardware and serving line 93, hardware and serving line 94
  59. arXiv 2608.24070arxiv.orgCited in the survey line 47, low-bit numerics line 130, low-bit numerics line 131
  60. arXivarxiv.orgCited in moe and conditional compute line 135
  61. arXiv 2609.16338arxiv.orgCited in the survey line 43, the survey line 47, low-bit numerics line 22, low-bit numerics line 23, low-bit numerics line 33, low-bit numerics line 55, low-bit numerics line 56, low-bit numerics line 132, low-bit numerics line 151
  62. DeepSeek-V4.1-Flasharxiv.orgCited in low-bit numerics line 93
  63. Cartridges++arxiv.orgCited in the design line 128, the design line 195
  64. Dual-QKarxiv.orgCited in low-bit numerics line 93
  65. Decryptdecrypt.coCited in the survey line 71, decoding and test-time compute line 62, decoding and test-time compute line 77, decoding and test-time compute line 168
  66. DeepLearning.AI The Batchdeeplearning.aiCited in attention and kv cache line 40
  67. DeepMinddeepmind.googleCited in the survey line 71, decoding and test-time compute line 76
  68. Red Hatdevelopers.redhat.comCited in the survey line 47, low-bit numerics line 129
  69. EE Timeseetimes.comCited in the survey line 87, the survey line 89, hardware and serving line 36, hardware and serving line 60, hardware and serving line 61, hardware and serving line 62, hardware and serving line 63, hardware and serving line 64, hardware and serving line 66, hardware and serving line 139
  70. Emergent Mind summary of arXiv 2502.06703emergentmind.comCited in decoding and test-time compute line 162
  71. Emergent Mind summary of DeepSeek-R1 paperemergentmind.comCited in distillation and cost trends line 83
  72. Wikipedia, 1.58-bit LLMen.wikipedia.orgCited in low-bit numerics line 26, low-bit numerics line 32, low-bit numerics line 113
  73. Epoch AIepoch.aiCited in distillation and cost trends line 29, distillation and cost trends line 30, distillation and cost trends line 84, distillation and cost trends line 145
  74. Epoch AIepoch.aiCited in distillation and cost trends line 82
  75. Epoch AIepoch.aiCited in the survey line 25, distillation and cost trends line 38, distillation and cost trends line 39
  76. Epoch AIepoch.aiCited in the survey line 9, the survey line 23, the survey line 25, decoding and test-time compute line 128, decoding and test-time compute line 167, distillation and cost trends line 10, distillation and cost trends line 11, distillation and cost trends line 12, distillation and cost trends line 13, distillation and cost trends line 14, distillation and cost trends line 15, distillation and cost trends line 147, distillation and cost trends line 150
  77. FourWeekMBAfourweekmba.comCited in hardware and serving line 33
  78. Maxim AI on LLaDA2.1getmaxim.aiCited in decoding and test-time compute line 88
  79. microsoft/BitNetgithub.comCited in the survey line 43, low-bit numerics line 20, low-bit numerics line 21, low-bit numerics line 54
  80. Graphcore Researchgraphcore-research.github.ioCited in the survey line 55, moe and conditional compute line 131
  81. HF DeepSeek-V4huggingface.coCited in the survey line 11, the survey line 63, attention and kv cache line 55, attention and kv cache line 137, attention and kv cache line 170, attention and kv cache line 186
  82. HF/NVIDIAhuggingface.coCited in the survey line 65, attention and kv cache line 28, attention and kv cache line 187
  83. Hugging Face model cardhuggingface.coCited in moe and conditional compute line 12, moe and conditional compute line 114, moe and conditional compute line 155
  84. HF Papershuggingface.coCited in the survey line 53, distillation and cost trends line 100, distillation and cost trends line 101, distillation and cost trends line 102, distillation and cost trends line 103, distillation and cost trends line 104, distillation and cost trends line 105, distillation and cost trends line 127
  85. ICLR 2026 oraliclr.ccCited in attention and kv cache line 37
  86. Memory Layers at Scaleicml.ccCited in the design line 42, the design line 194
  87. Inception bloginceptionlabs.aiCited in decoding and test-time compute line 63
  88. Inception, Introducing Mercuryinceptionlabs.aiCited in decoding and test-time compute line 60
  89. Introl summaryintrol.comCited in the design line 42
  90. Kaitchupkaitchup.substack.comCited in attention and kv cache line 17, attention and kv cache line 138
  91. Let's Data Scienceletsdatascience.comCited in the survey line 71, decoding and test-time compute line 70
  92. LMSYSlmsys.orgCited in the survey line 33, the survey line 53, moe and conditional compute line 66
  93. LMSYS blog, Dec 1 2025lmsys.orgCited in decoding and test-time compute line 17
  94. LMSYSlmsys.orgCited in moe and conditional compute line 91
  95. LMSYSlmsys.orgCited in the survey line 71, decoding and test-time compute line 83
  96. Apple ML Researchmachinelearning.apple.comCited in distillation and cost trends line 106
  97. Raschka, "A Dream of Spring for Open-Weight LLMs" (Jan-Feb 2026 architectures)magazine.sebastianraschka.comCited in attention and kv cache line 15, attention and kv cache line 16, attention and kv cache line 56, attention and kv cache line 57, attention and kv cache line 58, attention and kv cache line 108, attention and kv cache line 169
  98. Marginal Revolution summarymarginalrevolution.comCited in distillation and cost trends line 13
  99. MiniMaxminimax.ioCited in the survey line 65, attention and kv cache line 108, attention and kv cache line 198
  100. NeurIPS 2026neurips.ccCited in moe and conditional compute line 164
  101. SemiAnalysisnewsletter.semianalysis.comCited in distillation and cost trends line 128, distillation and cost trends line 149
  102. SemiAnalysisnewsletter.semianalysis.comCited in the survey line 7, the survey line 35, the survey line 81, the survey line 85, hardware and serving line 14, hardware and serving line 15, hardware and serving line 16, hardware and serving line 17, hardware and serving line 18, hardware and serving line 21, hardware and serving line 39, hardware and serving line 96, hardware and serving line 120, hardware and serving line 121, hardware and serving line 138
  103. Photonics Onlinephotonicsonline.comCited in hardware and serving line 73
  104. PrismMLprismml.comCited in the survey line 43, low-bit numerics line 24, low-bit numerics line 59
  105. ICLR 2025proceedings.iclr.ccCited in distillation and cost trends line 100
  106. PMLRproceedings.mlr.pressCited in moe and conditional compute line 35
  107. NeurIPS 2025proceedings.neurips.ccCited in hardware and serving line 70
  108. Pulsepulse.botCited in the survey line 87, hardware and serving line 37
  109. NVIDIA Researchresearch.nvidia.comCited in the survey line 41, the survey line 47, low-bit numerics line 16, low-bit numerics line 17, low-bit numerics line 64, low-bit numerics line 65, low-bit numerics line 87, low-bit numerics line 88, low-bit numerics line 89, low-bit numerics line 112
  110. NYU Shanghai RITSrits.shanghai.nyu.eduCited in low-bit numerics line 69, low-bit numerics line 152
  111. AMD ROCm blogrocm.blogs.amd.comCited in low-bit numerics line 150
  112. Semiconductor Engineeringsemiengineering.comCited in the survey line 89, hardware and serving line 70, hardware and serving line 140
  113. Shattered.ioshattered.ioCited in hardware and serving line 33
  114. SiliconANGLEsiliconangle.comCited in the survey line 89, hardware and serving line 65, hardware and serving line 66, hardware and serving line 95
  115. Silicon Reportsiliconreport.comCited in the survey line 7, the survey line 11, the survey line 69, the survey line 85, the survey line 87, the design line 23, the design line 196, hardware and serving line 12, hardware and serving line 13, hardware and serving line 22, hardware and serving line 23, hardware and serving line 24, hardware and serving line 25, hardware and serving line 26, hardware and serving line 30, hardware and serving line 31, hardware and serving line 39, hardware and serving line 118, hardware and serving line 119, hardware and serving line 122, hardware and serving line 141
  116. IEEE Spectrumspectrum.ieee.orgCited in the survey line 89, hardware and serving line 69
  117. Spheron, "MoE cost per token: why active parameters set your GPU bill"spheron.networkCited in moe and conditional compute line 80
  118. Spheron on vLLM NVFP4 KVspheron.networkCited in low-bit numerics line 93
  119. StorageReviewstoragereview.comCited in the survey line 81, hardware and serving line 29, hardware and serving line 32, hardware and serving line 117, hardware and serving line 122
  120. The Decoderthe-decoder.comCited in the survey line 63, attention and kv cache line 40, attention and kv cache line 157, attention and kv cache line 167
  121. The Quantum Insiderthequantuminsider.comCited in the survey line 89, hardware and serving line 73, hardware and serving line 142
  122. tianpan.co, "MoE serving production quirks" (Apr 2026)tianpan.coCited in moe and conditional compute line 80
  123. Together AI Mamba-3 blogtogether.aiCited in attention and kv cache line 37, attention and kv cache line 93
  124. Tom's Hardwaretomshardware.comCited in the survey line 85, low-bit numerics line 148
  125. Tsinghua Universitytsinghua.edu.cnCited in distillation and cost trends line 61
  126. VentureBeatventurebeat.comCited in the survey line 51, moe and conditional compute line 23, moe and conditional compute line 77, moe and conditional compute line 167
  127. VentureBeatventurebeat.comCited in attention and kv cache line 157
  128. victorgrosser.nlvictorgrosser.nlCited in the survey line 51, moe and conditional compute line 21
  129. vLLMvllm.aiCited in the survey line 47, the survey line 65, attention and kv cache line 136, attention and kv cache line 197
  130. vLLM DeepSeek-V4 blogvllm.aiCited in attention and kv cache line 55