Codellama requires bf16 for now (error to convert from bf16 to f16).
Multiprocess demo not functional for it because flash-attn only supports
f16 for now.
* 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.
* Refactor the llama example to make it more in sync with the other ones.
* Make clippy happy.
* Properly load the safetensor weights.
* Get llama back to a working state for the safetensors case.
- `api::Api` -> `api::tokio::api` (And created new `api::sync::Api`).
- Remove `tokio` from all our examples.
- Using similar codebase for now instead of ureq (for simplicity).
* Fix some rebase issues.
* Use mkl instead.
* Use mkl in bert.
* Add the optional mkl feature.
* Conditional compilation based on the mkl feature.
* Add more mkl support.
