mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-24 16:32:12 +00:00
Add support for Phi-3-medium The main difference between the medium and mini models is that medium uses grouped query attention with a packed QKV matrix. This change adds support for GQA with packed matrixes to `Weights.get_weights_col_packed` and uses it for Phi-3. This also allows us to remove the custom implementation of GQA from dbrx attention loading. |
||
---|---|---|
.. | ||
custom_kernels | ||
exllama_kernels | ||
exllamav2_kernels | ||
tests | ||
text_generation_server | ||
.gitignore | ||
Makefile | ||
Makefile-awq | ||
Makefile-eetq | ||
Makefile-flash-att | ||
Makefile-flash-att-v2 | ||
Makefile-marlin | ||
Makefile-selective-scan | ||
Makefile-vllm | ||
poetry.lock | ||
pyproject.toml | ||
README.md | ||
requirements_cuda.txt | ||
requirements_intel.txt | ||
requirements_rocm.txt |
Text Generation Inference Python gRPC Server
A Python gRPC server for Text Generation Inference
Install
make install
Run
make run-dev