Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Titanium partner change, blog edit. #3037

Merged
merged 6 commits into from
Jul 1, 2024
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
Fix formatting issue in the table for fp16 blog
Signed-off-by: Naveen Tatikonda <[email protected]>
naveentatikonda committed Jun 28, 2024

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
commit 8b68d1ecaf73b899a08996e4f88d8f9fc426704c
Original file line number Diff line number Diff line change
@@ -193,15 +193,17 @@
|Force merge segments |1 |1 |
|Client instance |r5.16xlarge |r5.16xlarge |

Config ID |Optimization strategy |m |ef_construction |ef_search |
|--- |--- |--- |--- |--- |
|hnsw1 |Default configuration |16 |100 |100 |
|hnsw2 |Balance between latency, memory, and recall |16 |128 |128 |
|hnsw3 |Optimize for recall |16 |256 |256 |

Faiss HNSW SQfp16 requires 4 data nodes---half the number needed for Faiss HNSW (8). This demonstrates that SQfp16 reduces memory requirements by 50%.
Faiss HNSW SQfp16 requires 4 data nodes---half the number needed for Faiss HNSW (8). This demonstrates that SQfp16 reduces memory requirements by 50%.
For more information about estimating the required memory and number of data nodes, see the [Appendix](#appendix-memory-and-data-node-requirement-estimation).


| Config ID |Optimization strategy |m |ef_construction |ef_search |

Check failure on line 201 in _posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md

GitHub Actions / style-job

[vale] reported by reviewdog 🐶 [OpenSearch.TableHeadings] 'm' is a table heading and should be in sentence case. Raw Output: {"message": "[OpenSearch.TableHeadings] 'm' is a table heading and should be in sentence case.", "location": {"path": "_posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md", "range": {"start": {"line": 201, "column": 38}}}, "severity": "ERROR"}

Check failure on line 201 in _posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md

GitHub Actions / style-job

[vale] reported by reviewdog 🐶 [OpenSearch.TableHeadings] 'ef_construction' is a table heading and should be in sentence case. Raw Output: {"message": "[OpenSearch.TableHeadings] 'ef_construction' is a table heading and should be in sentence case.", "location": {"path": "_posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md", "range": {"start": {"line": 201, "column": 41}}}, "severity": "ERROR"}

Check failure on line 201 in _posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md

GitHub Actions / style-job

[vale] reported by reviewdog 🐶 [OpenSearch.Spelling] Error: ef_construction. If you are referencing a setting, variable, format, function, or repository, surround it with tic marks. Raw Output: {"message": "[OpenSearch.Spelling] Error: ef_construction. If you are referencing a setting, variable, format, function, or repository, surround it with tic marks.", "location": {"path": "_posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md", "range": {"start": {"line": 201, "column": 41}}}, "severity": "ERROR"}

Check failure on line 201 in _posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md

GitHub Actions / style-job

[vale] reported by reviewdog 🐶 [OpenSearch.Spelling] Error: ef_search. If you are referencing a setting, variable, format, function, or repository, surround it with tic marks. Raw Output: {"message": "[OpenSearch.Spelling] Error: ef_search. If you are referencing a setting, variable, format, function, or repository, surround it with tic marks.", "location": {"path": "_posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md", "range": {"start": {"line": 201, "column": 58}}}, "severity": "ERROR"}

Check failure on line 201 in _posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md

GitHub Actions / style-job

[vale] reported by reviewdog 🐶 [OpenSearch.TableHeadings] 'ef_search' is a table heading and should be in sentence case. Raw Output: {"message": "[OpenSearch.TableHeadings] 'ef_search' is a table heading and should be in sentence case.", "location": {"path": "_posts/2024-06-19-optimizing-opensearch-with-fp16-quantization.md", "range": {"start": {"line": 201, "column": 58}}}, "severity": "ERROR"}
|------------|--- |--- |--- |--- |
| hnsw1 |Default configuration |16 |100 |100 |
| hnsw2 |Balance between latency, memory, and recall |16 |128 |128 |
| hnsw3 |Optimize for recall |16 |256 |256 |

#### Recall and memory results

|Experiment ID |hnsw-recall@1000 |hnsw-sqfp16-recall@1000 |hnsw memory usage (gb) |hnsw-sqfp16 memory usage (gb) |% reduction in memory |