HyInv report: BF16 speed-up against the reference sampler
Reference sampler speedup bf16 of HyInv
Section 4 states HyInv designs 128 sequences for a 402-residue backbone in 50.6 ms on one NVIDIA H20, '52.1x faster than the reference implementation of the sampler and 57x faster than ProteinMPNN'; the abstract gives the same figure as 'about 52x faster than the reference sampler'. This is HyInv's optimised BF16 path against HyInv's own FP32 reference sampler, not against a baseline model, and it is the printed ratio of the two Table 1 times for the 402-residue request (2,633 and 50.6 ms). The 57x recorded as a result is the ratio against ProteinMPNN's released implementation. Both were timed with the supervised-stage weights at rewrite temperature 0.23, not the released checkpoint.
Descriptive fact read from the pinned sources at the locator given. Not a measurement on a benchmark panel.
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.
12 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Claimed field reference_sampler_speedup_bf16 Context-only references | HyInv package README (Tencent Hunyuan, commit 0dcc533c) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: GitHub repository Tencent-Hunyuan/Hyra-results at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Claimed field reference_sampler_speedup_bf16 Context-only references | HyInv Technical Report (Hyra Team, 2026-10-14) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted. |
| Source location Section 4 'Efficient inference', first sentence; abstract Context-only references | HyInv package README (Tencent Hunyuan, commit 0dcc533c) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: GitHub repository Tencent-Hunyuan/Hyra-results at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Source location Section 4 'Efficient inference', first sentence; abstract Context-only references | HyInv Technical Report (Hyra Team, 2026-10-14) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted. |
| Claimed value Section 4 states HyInv designs 128 sequences for a 402-residue backbone in 50.6 ms on one NVIDIA H20, '52.1x faster than the reference implementation of the sampler and 57x faster than ProteinMPNN'; the abstract gives the same figure as 'about 52x faster than the reference sampler'. This is HyInv's optimised BF16 path against HyInv's own FP32 reference sampler, not against a baseline model, and it is the printed ratio of the two Table 1 times for the 402-residue request (2,633 and 50.6 ms). The 57x recorded as a result is the ratio against ProteinMPNN's released implementation. Both were timed with the supervised-stage weights at rewrite temperature 0.23, not the released checkpoint. Context-only references | HyInv package README (Tencent Hunyuan, commit 0dcc533c) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: GitHub repository Tencent-Hunyuan/Hyra-results at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Claimed value Section 4 states HyInv designs 128 sequences for a 402-residue backbone in 50.6 ms on one NVIDIA H20, '52.1x faster than the reference implementation of the sampler and 57x faster than ProteinMPNN'; the abstract gives the same figure as 'about 52x faster than the reference sampler'. This is HyInv's optimised BF16 path against HyInv's own FP32 reference sampler, not against a baseline model, and it is the printed ratio of the two Table 1 times for the 402-residue request (2,633 and 50.6 ms). The 57x recorded as a result is the ratio against ProteinMPNN's released implementation. Both were timed with the supervised-stage weights at rewrite temperature 0.23, not the released checkpoint. Context-only references | HyInv Technical Report (Hyra Team, 2026-10-14) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted. |
| Description Descriptive fact read from the pinned sources at the locator given. Not a measurement on a benchmark panel. Context-only references | HyInv package README (Tencent Hunyuan, commit 0dcc533c) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: GitHub repository Tencent-Hunyuan/Hyra-results at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Description Descriptive fact read from the pinned sources at the locator given. Not a measurement on a benchmark panel. Context-only references | HyInv Technical Report (Hyra Team, 2026-10-14) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted. |
| Relationship: subject hyinv-20261106-model-hyinv Context-only references | HyInv package README (Tencent Hunyuan, commit 0dcc533c) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: GitHub repository Tencent-Hunyuan/Hyra-results at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: subject hyinv-20261106-model-hyinv Context-only references | HyInv Technical Report (Hyra Team, 2026-10-14) Section 4 'Efficient inference', first sentence; abstract Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages) | not individually reviewed No individual claim review recorded Source has a recorded evidence concern. Consult its source page before using the claim. Audit detailsField: Source artifact SHA-256: Hash scope: pdftotext -layout text layer, parsed by extract/parse.py with every row label and column count asserted. |
Sources and history
Release 2026-11-21-c8bea25e5abb · Record review: source checked
2 source records and release history
- HyInv Technical Report (Hyra Team, 2026-10-14) · Original source · Dated 2026-10-14; retrieved at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a (21 pages)
- HyInv package README (Tencent Hunyuan, commit 0dcc533c) · Original source · GitHub repository Tencent-Hunyuan/Hyra-results at commit 0dcc533cc9f8f76c90ecbfe944df816b6672328a
Technical metadata and extraction receipts
Stable ID: hyinv-20261106-claim-hyinv-reference-sampler-speedup-bf16
- areas
- proteins-complexes; protein-structure
- contexts
- research
- field
- reference_sampler_speedup_bf16
- review
- artifact sha256: 0f10b390be399c341d1f7497c5a3ca0ac857ce78172c4732bdc86a9c66e46419; method: independent-cell-check; deterministic-table-parse; pdf-text-parse; source-hash-verification; method note: Independent review pass. The pinned PDF was re-downloaded at the pinned commit and its SHA-256 checked against the source record; pdftotext -layout reproduced the archived text layer byte for byte. npm run batch -- check-values was run over the whole batch against that text layer (value-check.tsv). The 170 cells of Tables 6, 7, 8 and 9 and the 290 cells of the Figure 14 and Figure 15 matrices were then re-read by a reviewer script that finds each row by its printed label and splits the printed cells by position, written for this pass without using the extractor's parser; every printed value and column matched. Column assignment in Figure 14 was confirmed against the labelled columns of Table 2 and against Section 5.2's prose figures; Figure 15's was confirmed by the coordinator reading the rotated column headers on the rendered page 17, which match Figure 14's order. Table 1, Figure 4a and the eleven prose values were read by hand against the text layer. Each claim was re-read against the passage its locator names.; retrieval url: https://raw.githubusercontent.com/Tencent-Hunyuan/Hyra-results/0dcc533cc9f8f76c90ecbfe944df816b6672328a/AI4Science/hyinv/HyInv_Technical_Report.pdf; reviewed at: 2026-11-06T00:00:00Z; reviewer: claude; reviewer note: Claude research agent; no human review claimed. Reviewed by a different agent from the one that extracted the batch. Transcription checked against the pinned source; nothing was reproduced and no value was recomputed.
- source locator
- Section 4 'Efficient inference', first sentence; abstract
- value
- Section 4 states HyInv designs 128 sequences for a 402-residue backbone in 50.6 ms on one NVIDIA H20, '52.1x faster than the reference implementation of the sampler and 57x faster than ProteinMPNN'; the abstract gives the same figure as 'about 52x faster than the reference sampler'. This is HyInv's optimised BF16 path against HyInv's own FP32 reference sampler, not against a baseline model, and it is the printed ratio of the two Table 1 times for the 402-residue request (2,633 and 50.6 ms). The 57x recorded as a result is the ratio against ProteinMPNN's released implementation. Both were timed with the supervised-stage weights at rewrite temperature 0.23, not the released checkpoint.
Related records
- subject: HyInv