- Add ms/token on llama2.c (15ms/token on my personal machine)
- Hide `Run` buttons while models are not ready
- Add dummy `progress` while weights are downloading (I briefly looked
at putting a real progressbar.. and nothing easy enough came up.)
* 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.
* 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.
