* Cuda support for the mnist training.
* min/max fix + testing.
* Add the argmin/argmax tests.
* More cuda support for argmin/argmax.
* Cuda kernels for argmin and argmax.
* Start sketching the bigcode gpt model.
* Sketch the bigcode model.
* Implement the attention mechanism.
* Random reshaping.
* Sketch more of the example.
* Add some kv cache.
* Properly generate the position ids.
* Proper attention mask.
* Bail on upcasting.
* Properly apply the attention mask.
* Add the smaller starcoder variants.
* Update for the new hub api.
* Fix a shape issue.
* Fix another shape issue.
* Get some logits out.
* Adjust the weigth names.
* Again set a few extra params.
* Use the appropriate kernel sizes.
* Add all the kernel sizes.
* Parallel compiling.
* Reduce the amount of parallelism.
* Add the missing kernel.
* Fix a typo.
* Remove bf16 support for now.
* Proper flash-attn parameters.
* Set the flash attention parameters.
* Add more validations.
* Setup the o_ flash attn parameters.
* More flash-attn support.
* Set more flash attn parameters.
* 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.
* 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.
* 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.
