Repository navigation
Commit 1a78804
authored
Qualcomm AI Engine Direct - HF LLM lm_eval lazy import (pytorch#20413)
### Summary
When importing HF LLM lowering flow from QNN, Optimum-ExecuTorch will
run into lm_eval import error. To resolve this issue, we need to make
lm_eval lazily imported, meaning we only import when we actually use the
library.
### Test plan
NA1 parent 3c359d4 commit 1a78804
1 file changed
Lines changed: 11 additions & 10 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
171 | 171 | | |
172 | 172 | | |
173 | 173 | | |
174 | | - | |
175 | | - | |
176 | | - | |
177 | | - | |
178 | | - | |
179 | | - | |
180 | | - | |
181 | | - | |
182 | | - | |
183 | | - | |
184 | 174 | | |
185 | 175 | | |
186 | 176 | | |
| |||
211 | 201 | | |
212 | 202 | | |
213 | 203 | | |
| 204 | + | |
| 205 | + | |
| 206 | + | |
| 207 | + | |
| 208 | + | |
| 209 | + | |
| 210 | + | |
| 211 | + | |
| 212 | + | |
| 213 | + | |
| 214 | + | |
214 | 215 | | |
215 | 216 | | |
216 | 217 | | |
| |||
0 commit comments