hf_text-generation-inference/launcher
Daniël de Kok 2358c2bb54
Add basic FP8 KV cache support (#2603)
* Add basic FP8 KV cache support

This change adds rudimentary FP8 KV cache support. The support is
enabled by passing `--kv-cache-dtype fp8_e5m2` to the launcher. Doing so
uses this type for the KV cache. However support is still limited:

* Only the `fp8_e5m2` type is supported.
* The KV cache layout is the same as `float16`/`bfloat16` (HND).
* The FP8 KV cache is only supported for FlashInfer.
* Loading of scales is not yet supported.

* Fix Cargo.toml
2024-10-04 17:51:48 +02:00
..
src Add basic FP8 KV cache support (#2603) 2024-10-04 17:51:48 +02:00
Cargo.toml CI (2592): Allow LoRA adapter revision in server launcher (#2602) 2024-10-02 10:51:04 -04:00
build.rs chore(github): add templates (#264) 2023-05-02 15:43:19 +02:00