Releases: explosion/thinc
Releases · explosion/thinc
v8.0.12: Bug fixes for set_ops and use_ops
v8.0.11: Improved GPU training time
✨ New features and improvements
- Speed up GPU training time with up to ~25% by using cuBLAS for computing Frobenius norms in gradient clipping.
- Give preference to
AppleOps
(if available) when callingget_ops("cpu")
. - Support missing values in
CategoricalCrossEntropy
when the labels are integers. - Provide the option to run
model.walk
with depth-first traversal. - Wrap
forward
/init
callbacks of aModel
inwith_debug
andwith_nvtx_range
to facilitate recursively instrumenting models.
🔴 Bug fixes
- Fix issue #537: Fix
replace_node
on nodes with indirect node refs.
👥 Contributors
v8.0.10: Bug fix for get_array_ops
v8.0.9: Support for NVTX ranges and mypy plugin fixes
✨ New features and improvements
- Add
ops
registry. - Enable config overrides to add new keys.
- Allow newer releases of
nbconvert
andnbformat
. - Layer for marking NVTX ranges.
- Support mixed-precision training in the PyTorch shim (experimental).
🔴 Bug fixes
- Fix issue #521: Fix
numpy_ops
gemm
output. - Fix issue #525: Fix
mypy
plugin crash on variadic arguments.
👥 Contributors
@adrianeboyd, @connorbrinton, @danieldk, @honnibal, @ines, @svlandeg
v8.0.8: CategoricalCrossentropy allows negated values
✨ New features and improvements
- Allow negated values in CategoricalCrossentropy
v8.0.7: Bug fixes for n-grams and typing
v8.0.6: Bug fix for backprop_reduce_max GPU kernel
🔴 Bug fixes
- Fix
backprop_reduce_max
GPU kernel.
v8.0.5: Updates for torch v1.9.0
✨ New features and improvements
- Update to support torch v1.9.0.
v8.0.4: New tuplify and resizable layers, and some bug fixes
✨ New features and improvements
- Add
tuplify
layer. - More generic implementation of the
concatenate
layer. - Add
resizable
layer. - Introduce
force
parameter formodel.set_dim()
. - Improve UX when setting the GPU allocator.
🔴 Bug fixes
- Fix issue #492: Fix backpropagation in
with_getitem
. - Fix issue #494: Resolve forward refs issue with Pydantic.
- Fix issue #496: Avoid Pydantic versions with security vulnerabilities.
👥 Contributors
@adrianeboyd, @honnibal, @ines, @Kludex, @polm, @svlandeg, @thomashacker