Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
hf_text-generation-inference/docs/source/reference
History
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
..
api_reference.md doc: Add metrics documentation and add a 'Reference' section (#2230) 2024-08-16 19:43:30 +02:00
launcher.md Add basic FP8 KV cache support (#2603) 2024-10-04 17:51:48 +02:00
metrics.md doc: Add metrics documentation and add a 'Reference' section (#2230) 2024-08-16 19:43:30 +02:00