huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-23 07:52:06 +00:00
Code Issues Packages Projects Releases Wiki Activity
b36c0f8436
text-generation-inference/server
History
drbh d888bc2828 feat: support force downcast after FastRMSNorm multiply for Gemma (#1658) 
This PR adds `force_downcast_after` to `FastRMSNorm.forward` which is
used in the Gemma model. References
https://github.com/huggingface/transformers/pull/29402 and
https://github.com/huggingface/transformers/pull/29729

Setting `force_downcast_after=True` will perform the `hidden_states *
weight` multiplication in f32 and then downcast to half. This differs
slightly from the current implementation which first casts the
`hidden_states` to a half and then multiples.
2024-04-25 12:32:42 +03:00
..
custom_kernels chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
exllama_kernels chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
exllamav2_kernels chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
tests feat(server): add frequency penalty (#1541) 2024-04-24 08:43:50 +00:00
text_generation_server feat: support force downcast after FastRMSNorm multiply for Gemma (#1658) 2024-04-25 12:32:42 +03:00
.gitignore Impl simple mamba model (#1480) 2024-04-23 11:45:11 +03:00
Makefile Update peft + transformers + accelerate + bnb + safetensors (#1646) 2024-04-25 11:49:44 +03:00
Makefile-awq chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
Makefile-eetq feat: eetq gemv optimization when batch_size <= 4 (#1502) 2024-04-23 09:20:14 +03:00
Makefile-flash-att chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
Makefile-flash-att-v2 make install-flash-attn-v2-cuda should work like make install-flash-attn-v2 used to work. (#1294) 2023-11-28 16:28:40 +01:00
Makefile-selective-scan chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
Makefile-vllm Speculative (#1308) 2024-04-18 12:39:39 +00:00
poetry.lock Update peft + transformers + accelerate + bnb + safetensors (#1646) 2024-04-25 11:49:44 +03:00
pyproject.toml Update peft + transformers + accelerate + bnb + safetensors (#1646) 2024-04-25 11:49:44 +03:00
README.md chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
requirements_common.txt Add RoCm support (#1243) 2023-11-27 14:08:12 +01:00
requirements_cuda.txt v1.4.1 (#1568) 2024-04-24 15:42:59 +03:00
requirements_rocm.txt v1.4.1 (#1568) 2024-04-24 15:42:59 +03:00
requirements.txt Update peft + transformers + accelerate + bnb + safetensors (#1646) 2024-04-25 11:49:44 +03:00

README.md

Text Generation Inference Python gRPC Server

A Python gRPC server for Text Generation Inference

Install

make install

Run

make run-dev