GenomeOcean-4B, FP8 KV cache, vLLM generation (Yu et al. 2026)
Protocol B.1: FP8 E4M3 KV cache with dynamic per-tensor scaling; weights and activations BF16.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluations and results
1 evaluation · 4 results. Different protocols are not a single leaderboard.
Protocol: GenomeOcean-4B autoregressive generation throughput, power, energy efficiency and perplexity, BF16 versus FP8 (Yu et al. 2026 Table 4) · Dataset: 96 GTDB Bacteria genome sequences bounded to 102,400 tokens (Yu et al. 2026)
Sorted by Energy efficiency (Autoregressive generation; generated tokens per second per watt) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
| Tested configuration | Energy efficiency (Autoregressive generation; generated tokens per second per watt) | Inference throughput (Autoregressive generation; generated tokens per second) | Perplexity (Sliding-window perplexity on 96 GTDB Bacteria sequences (10,240-token context, 2,560-token stride)) | Power draw (Autoregressive generation; mean steady-state GPU power from NVML) |
|---|---|---|---|---|
| GenomeOcean-4B, FP8 KV cache, vLLM generation (Yu et al. 2026)Evaluation | 3.14 ± 0.02 | 2085.89 ± 34.49 | 126.63 ± 1.04 | 663.77 ± 8.84 |
All 4 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.
Use this configuration
How it works, versions and access
Strengths, limitations and unresolved questions
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- FP8 Inference in Genomic Foundation Models: Theoretical vs. Realized Speedups on GenomeOcean · Original source · bioRxiv preprint version 1, posted 2026-08-14 (PDF footer); bioRxiv API date 2026-08-18
Technical metadata and extraction receipts
Stable ID: model-execution-20261011-config-yu2026-genomeocean-4b-fp8-kv-vllm
- areas
- dna-genomes
- contexts
- research
- method types
- foundation_model
- reported name
- 4B FP8 KV cache
- foundation model eligible
- true
- version
- GenomeOcean-4B
- parameters
- 4B parameters
- access reuse
- Checkpoint release not stated in this source; benchmarking code at https://github.com/jgi-genomeocean/genomeocean_efficiency (not pinned)
- hardware
- description: One NVIDIA H100 SXM5 GPU, 80 GB HBM3 (Section 2.2)
- protocol
- Protocol B.1: FP8 E4M3 KV cache with dynamic per-tensor scaling; weights and activations BF16.
- source locator
- Sections 2.1-2.4; Table 1; Table 2
Related records
- configuration of: GenomeOcean
- system: GenomeOcean-4B FP8 KV-Cache generation (Yu et al. 2026)