[inference] speedup by 84% - async, layer caching #103
34.14% of diff hit (target 7.98%)
View this Pull Request on Codecov
34.14% of diff hit (target 7.98%)
Annotations
Check warning on line 165 in apps/inference/neuronpedia_inference/endpoints/activation/all.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/all.py#L165
Added line #L165 was not covered by tests
Check warning on line 177 in apps/inference/neuronpedia_inference/endpoints/activation/all.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/all.py#L177
Added line #L177 was not covered by tests
Check warning on line 181 in apps/inference/neuronpedia_inference/endpoints/activation/all.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/all.py#L180-L181
Added lines #L180 - L181 were not covered by tests
Check warning on line 184 in apps/inference/neuronpedia_inference/endpoints/activation/all.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/all.py#L183-L184
Added lines #L183 - L184 were not covered by tests
Check warning on line 186 in apps/inference/neuronpedia_inference/endpoints/activation/all.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/all.py#L186
Added line #L186 was not covered by tests
Check warning on line 188 in apps/inference/neuronpedia_inference/endpoints/activation/all.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/all.py#L188
Added line #L188 was not covered by tests
Check warning on line 191 in apps/inference/neuronpedia_inference/endpoints/activation/all.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/all.py#L191
Added line #L191 was not covered by tests
Check warning on line 157 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L157
Added line #L157 was not covered by tests
Check warning on line 160 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L160
Added line #L160 was not covered by tests
Check warning on line 163 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L163
Added line #L163 was not covered by tests
Check warning on line 167 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L166-L167
Added lines #L166 - L167 were not covered by tests
Check warning on line 170 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L169-L170
Added lines #L169 - L170 were not covered by tests
Check warning on line 172 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L172
Added line #L172 was not covered by tests
Check warning on line 270 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L270
Added line #L270 was not covered by tests
Check warning on line 273 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L273
Added line #L273 was not covered by tests
Check warning on line 276 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L276
Added line #L276 was not covered by tests
Check warning on line 279 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L279
Added line #L279 was not covered by tests
Check warning on line 281 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L281
Added line #L281 was not covered by tests
Check warning on line 284 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L284
Added line #L284 was not covered by tests
Check warning on line 286 in apps/inference/neuronpedia_inference/endpoints/activation/single.py
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/single.py#L286
Added line #L286 was not covered by tests
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/topk_by_token.py#L72-L73
Added lines #L72 - L73 were not covered by tests
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/topk_by_token.py#L76
Added line #L76 was not covered by tests
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/topk_by_token.py#L79-L80
Added lines #L79 - L80 were not covered by tests
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/topk_by_token.py#L82-L83
Added lines #L82 - L83 were not covered by tests
codecov / codecov/patch
apps/inference/neuronpedia_inference/endpoints/activation/topk_by_token.py#L85
Added line #L85 was not covered by tests