hf_text-generation-inference/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
..
custom_kernels All integration tests back everywhere (too many failed CI). (#2428) 2024-08-16 21:19:46 +02:00
exllama_kernels Update ROCM libs and improvements (#2579) 2024-09-30 10:54:32 +02:00
exllamav2_kernels Update ROCM libs and improvements (#2579) 2024-09-30 10:54:32 +02:00
tests Fix tokenization yi (#2507) 2024-09-11 22:41:56 +02:00
text_generation_server Add basic FP8 KV cache support (#2603) 2024-10-04 17:51:48 +02:00
.gitignore Impl simple mamba model (#1480) 2024-02-08 10:19:45 +01:00
Makefile Lots of improvements (Still 2 allocators) (#2449) 2024-08-29 16:29:01 +02:00
Makefile-awq chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
Makefile-eetq Upgrade EETQ (Fixes the cuda graphs). (#1729) 2024-04-12 08:15:28 +02:00
Makefile-exllamav2 Upgrading exl2. (#2415) 2024-08-14 11:58:08 +02:00
Makefile-fbgemm Add Directory Check to Prevent Redundant Cloning in Build Process (#2486) 2024-09-07 13:19:43 +02:00
Makefile-flash-att Hotfixing `make install`. (#2008) 2024-06-04 23:34:03 +02:00
Makefile-flash-att-v2 Update ROCM libs and improvements (#2579) 2024-09-30 10:54:32 +02:00
Makefile-flashinfer Prefix test - Different kind of load test to trigger prefix test bugs. (#2490) 2024-09-11 18:10:40 +02:00
Makefile-lorax-punica Enable multiple LoRa adapters (#2010) 2024-06-25 14:46:27 -04:00
Makefile-selective-scan chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
Makefile-vllm Update ROCM libs and improvements (#2579) 2024-09-30 10:54:32 +02:00
README.md chore: add pre-commit (#1569) 2024-02-16 11:58:58 +01:00
poetry.lock Mllama flash version (#2585) 2024-10-02 11:22:13 +02:00
pyproject.toml Mllama flash version (#2585) 2024-10-02 11:22:13 +02:00
requirements_cuda.txt Mllama flash version (#2585) 2024-10-02 11:22:13 +02:00
requirements_intel.txt Mllama flash version (#2585) 2024-10-02 11:22:13 +02:00
requirements_rocm.txt Mllama flash version (#2585) 2024-10-02 11:22:13 +02:00

README.md

Text Generation Inference Python gRPC Server

A Python gRPC server for Text Generation Inference

Install

make install

Run

make run-dev