* Add some flash-attn kernel, import the code for flash-attn v2 from Dao-AILab.
* More flash attn.
* Set up the flash attn parameters.
* Get things to compile locally.
* Move the flash attention files in a different directory.
* Build the static C library with nvcc.
* Add more flash attention.
* Update the build part.
* Better caching.
* Exclude flash attention from the default workspace.
* Put flash-attn behind a feature gate.
* Get the flash attn kernel to run.
* Move the flags to a more appropriate place.
* Enable flash attention in llama.
* Use flash attention in llama.
* Skeleton methods for IndexAdd/ScatterAdd.
* Add a Map2InPlace trait.
* Add the glue code for the index-add/scatter-add kernels.
* Tweak the file name: embeddings -> indexing.
* Add the cuda kernel for indexadd.
* And add the scatter-add kernels.
* Start adding llama2.c.
* Model loading.
* Add the llama-v2 model.
* Start converting the weights.
* Rotary embedding tweaks.
* Get the model to generate some tokens.
* Add the copy op.
* Tweak some cat error messages.
* Handle the contiguous case in to_vec1.
* Fast variant for to_vec2.
* Add add a faster to_vec3 variant.
* Cleanup some todos.
* Fix more todo.
* Optimize for the contiguous case.
* Add the IntDType trait.
* Handle the intdtype trait for more ops.
* Remove a todo.
* Remove a todo.
* Build example kernels.
* Add some sample custom kernel.
* Get the example kernel to compile.
* Add some cuda code.
* More cuda custom op.
* More cuda custom ops.
* Start adding gather.
* Gather cpu implementation + use in simple training.
* Add scatter_add for the gradient of gather.
* Simple cpu implementation of scatter_add.
* Use gather in the simple-training backprop.
* Refactor the reduce ops in order to introduce argmin/argmax.
* Clippy fixes.
* Use the newly introduced argmax.
* Fix the strided case.
* Handle the non-contiguous case.
* More realistic training setup.
* Compute the model accuracy.
* Very inefficient backprop for index select.
* More backprop.
* Fix some backprop issues.
* Backprop fix.
* Another broadcasting backprop fix.
* Better backprop for reducing ops.
* Training again.
* Add some gradient tests.
* Get the training to work.
* Add the comparison operations.
* Add the helper functions on the tensor side.
* More cmp operations.
* Cpu implementation for the comparison operations.
* Use contiguous tensors for variables.
* Sketch the mnist example.
* Start adding the reduce ops.
* Renaming.
* Refactor the reduce operations.
* Bugfix for the broadcasting vectorization.
