zygi
zygi
Modifies model and generation code to support key/value caching. This should mostly be a no-op in terms of behavior except for some numerical stability related changes. Tested locally. Semantic array...
**Describe the bug** In deep learning, people often use fp16 matmuls with fp32 accumulation (cuBLAS compute type) as a balance between performance and preserving numerical accuracy. In Torch, if you...
### Describe the feature Hi! Thanks for all the work, after the 04/15 patch I can now reproduce most of the SWE-bench instances using the default harness. However, I'm still...
Imagine I have the following xml: ``` Hello text_content_1 text_content_2 ... ``` That is, the metadata consists of a dynamic number of elements with dynamic tags and no attributes, each...
Hi, this isn't a bug report, just wanted to mention a solution to a potential problem some users might face. Could be useful to mention this in the wiki somewhere....
Expands mean curvature flow skeletonization, adds a method to return both the skeleton and the skeleton_vertex->orig_vertex mappings. (made it a separate method to not break the users of the existing...