text-generation-inference/server
Daniël de Kok c61ef1ce85 Factor out sharding of packed tensors (#2059)
For Phi-3-Small I need to shard a packed QKV bias tensor, for which
I implemented the `Weights.get_packed_sharded` method. However, this
method can also replace the `Weights._get_qweight` method and the
custom sharding code from `Weights.get_weights_col_packed`.
2024-09-24 03:46:09 +00:00
..
custom_kernels chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
exllama_kernels MI300 compatibility (#1764) 2024-07-17 05:36:58 +00:00
exllamav2_kernels chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
marlin Add support for GPTQ Marlin (#2052) 2024-09-24 03:43:30 +00:00
tests server: use chunked inputs 2024-09-24 03:42:29 +00:00
text_generation_server Factor out sharding of packed tensors (#2059) 2024-09-24 03:46:09 +00:00
.gitignore Impl simple mamba model (#1480) 2024-04-23 11:45:11 +03:00
Makefile Add support for GPTQ Marlin (#2052) 2024-09-24 03:43:30 +00:00
Makefile-awq chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
Makefile-eetq Upgrade EETQ (Fixes the cuda graphs). (#1729) 2024-04-25 17:58:27 +03:00
Makefile-flash-att Hotfixing make install. (#2008) 2024-09-24 03:29:29 +00:00
Makefile-flash-att-v2 Hotfixing make install. (#2008) 2024-09-24 03:29:29 +00:00
Makefile-selective-scan chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
Makefile-vllm Update LLMM1 bound (#2050) 2024-09-24 03:42:29 +00:00
poetry.lock Making make install work better by default. (#2004) 2024-09-24 03:29:29 +00:00
pyproject.toml Making make install work better by default. (#2004) 2024-09-24 03:29:29 +00:00
README.md chore: add pre-commit (#1569) 2024-04-24 15:32:02 +03:00
requirements_cuda.txt Modifing the version number. 2024-07-17 05:36:58 +00:00
requirements_intel.txt reable xpu, broken by gptq and setuptool upgrade (#1988) 2024-09-24 03:26:17 +00:00
requirements_rocm.txt Modifing the version number. 2024-07-17 05:36:58 +00:00

Text Generation Inference Python gRPC Server

A Python gRPC server for Text Generation Inference

Install

make install

Run

make run-dev