Repository navigation
Commit 3574bf1
authored
Arm backend: Relax Qwen3-VL 2B MXFP8 tolerance (pytorch#22590)
Parameterize MXFP comparison thresholds and relax them only for the
full-size 2B text model to account for accumulated quantization error.
cc @digantdesai @freddan80 @per @zingo @oscarandersson8218 @mansnils
@Sebastian-Larsson @robell @rascani
Signed-off-by: Sangwon Ha <sangwon.ha@arm.com>1 parent cfc6ecd commit 3574bf1
1 file changed
Lines changed: 9 additions & 3 deletions
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
314 | 314 | | |
315 | 315 | | |
316 | 316 | | |
| 317 | + | |
| 318 | + | |
317 | 319 | | |
318 | 320 | | |
319 | 321 | | |
| |||
326 | 328 | | |
327 | 329 | | |
328 | 330 | | |
329 | | - | |
330 | | - | |
| 331 | + | |
| 332 | + | |
331 | 333 | | |
332 | 334 | | |
333 | 335 | | |
| |||
404 | 406 | | |
405 | 407 | | |
406 | 408 | | |
407 | | - | |
| 409 | + | |
| 410 | + | |
| 411 | + | |
| 412 | + | |
| 413 | + | |
0 commit comments