hf_text-generation-inference/server/text_generation_server
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
..
adapters feat: add ruff and resolve issue (#2262) 2024-07-26 10:29:09 -04:00
layers Add basic FP8 KV cache support (#2603) 2024-10-04 17:51:48 +02:00
models Add basic FP8 KV cache support (#2603) 2024-10-04 17:51:48 +02:00
pb chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
utils Micro cleanup. (#2555) 2024-09-24 11:19:24 +02:00
__init__.py feat(clients): Python client (#103) 2023-03-07 18:52:22 +01:00
cache.py fix(server): decrease memory fragmentation (#557) 2023-07-06 14:28:33 +02:00
cli.py Add basic FP8 KV cache support (#2603) 2024-10-04 17:51:48 +02:00
interceptor.py v2.0.0 (#1736) 2024-04-12 18:38:34 +02:00
server.py Add basic FP8 KV cache support (#2603) 2024-10-04 17:51:48 +02:00
tracing.py Add OTLP Service Name Environment Variable (#2076) 2024-06-25 09:33:01 +02:00