From 0fd2ab3e89fbb8f4ddea30a280c96cb843a66074 Mon Sep 17 00:00:00 2001 From: David Holtz Date: Mon, 18 Nov 2024 21:48:09 +0000 Subject: [PATCH] fix: remove unused deps and imports --- docs/source/reference/launcher.md | 19 ++++++++++--------- server/requirements_cuda.txt | 1 - server/requirements_intel.txt | 1 - server/requirements_rocm.txt | 1 - .../models/custom_modeling/qwen2_vl.py | 2 +- 5 files changed, 11 insertions(+), 13 deletions(-) diff --git a/docs/source/reference/launcher.md b/docs/source/reference/launcher.md index da0c8717..da52d59a 100644 --- a/docs/source/reference/launcher.md +++ b/docs/source/reference/launcher.md @@ -62,15 +62,16 @@ Options: [env: QUANTIZE=] Possible values: - - awq: 4 bit quantization. Requires a specific AWQ quantized model: . Should replace GPTQ models wherever possible because of the better latency - - eetq: 8 bit quantization, doesn't require specific model. Should be a drop-in replacement to bitsandbytes with much better performance. Kernels are from - - exl2: Variable bit quantization. Requires a specific EXL2 quantized model: . Requires exllama2 kernels and does not support tensor parallelism (num_shard > 1) - - gptq: 4 bit quantization. Requires a specific GTPQ quantized model: . text-generation-inference will use exllama (faster) kernels wherever possible, and use triton kernel (wider support) when it's not. AWQ has faster kernels - - marlin: 4 bit quantization. Requires a specific Marlin quantized model: - - bitsandbytes: Bitsandbytes 8bit. Can be applied on any model, will cut the memory requirement in half, but it is known that the model will be much slower to run than the native f16 - - bitsandbytes-nf4: Bitsandbytes 4bit. Can be applied on any model, will cut the memory requirement by 4x, but it is known that the model will be much slower to run than the native f16 - - bitsandbytes-fp4: Bitsandbytes 4bit. nf4 should be preferred in most cases but maybe this one has better perplexity performance for you model - - fp8: [FP8](https://developer.nvidia.com/blog/nvidia-arm-and-intel-publish-fp8-specification-for-standardization-as-an-interchange-format-for-ai/) (e4m3) works on H100 and above This dtype has native ops should be the fastest if available. This is currently not the fastest because of local unpacking + padding to satisfy matrix multiplication limitations + - awq: 4 bit quantization. Requires a specific AWQ quantized model: . Should replace GPTQ models wherever possible because of the better latency + - compressed-tensors: Compressed tensors, which can be a mixture of different quantization methods + - eetq: 8 bit quantization, doesn't require specific model. Should be a drop-in replacement to bitsandbytes with much better performance. Kernels are from + - exl2: Variable bit quantization. Requires a specific EXL2 quantized model: . Requires exllama2 kernels and does not support tensor parallelism (num_shard > 1) + - gptq: 4 bit quantization. Requires a specific GTPQ quantized model: . text-generation-inference will use exllama (faster) kernels wherever possible, and use triton kernel (wider support) when it's not. AWQ has faster kernels + - marlin: 4 bit quantization. Requires a specific Marlin quantized model: + - bitsandbytes: Bitsandbytes 8bit. Can be applied on any model, will cut the memory requirement in half, but it is known that the model will be much slower to run than the native f16 + - bitsandbytes-nf4: Bitsandbytes 4bit. Can be applied on any model, will cut the memory requirement by 4x, but it is known that the model will be much slower to run than the native f16 + - bitsandbytes-fp4: Bitsandbytes 4bit. nf4 should be preferred in most cases but maybe this one has better perplexity performance for you model + - fp8: [FP8](https://developer.nvidia.com/blog/nvidia-arm-and-intel-publish-fp8-specification-for-standardization-as-an-interchange-format-for-ai/) (e4m3) works on H100 and above This dtype has native ops should be the fastest if available. This is currently not the fastest because of local unpacking + padding to satisfy matrix multiplication limitations ``` ## SPECULATE diff --git a/server/requirements_cuda.txt b/server/requirements_cuda.txt index 341c291c..29beb52b 100644 --- a/server/requirements_cuda.txt +++ b/server/requirements_cuda.txt @@ -36,7 +36,6 @@ protobuf==4.25.5 ; python_version >= "3.9" and python_version < "3.13" py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13" pygments==2.18.0 ; python_version >= "3.9" and python_version < "3.13" pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13" -qwen_vl_utils==0.0.8 ; python_version >= "3.9" and python_version < "3.13" regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13" requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13" rich==13.9.3 ; python_version >= "3.9" and python_version < "3.13" diff --git a/server/requirements_intel.txt b/server/requirements_intel.txt index 13863650..ad4ea56b 100644 --- a/server/requirements_intel.txt +++ b/server/requirements_intel.txt @@ -36,7 +36,6 @@ protobuf==4.25.5 ; python_version >= "3.9" and python_version < "3.13" py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13" pygments==2.18.0 ; python_version >= "3.9" and python_version < "3.13" pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13" -qwen_vl_utils==0.0.8 ; python_version >= "3.9" and python_version < "3.13" regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13" requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13" rich==13.9.3 ; python_version >= "3.9" and python_version < "3.13" diff --git a/server/requirements_rocm.txt b/server/requirements_rocm.txt index 13863650..ad4ea56b 100644 --- a/server/requirements_rocm.txt +++ b/server/requirements_rocm.txt @@ -36,7 +36,6 @@ protobuf==4.25.5 ; python_version >= "3.9" and python_version < "3.13" py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13" pygments==2.18.0 ; python_version >= "3.9" and python_version < "3.13" pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13" -qwen_vl_utils==0.0.8 ; python_version >= "3.9" and python_version < "3.13" regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13" requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13" rich==13.9.3 ; python_version >= "3.9" and python_version < "3.13" diff --git a/server/text_generation_server/models/custom_modeling/qwen2_vl.py b/server/text_generation_server/models/custom_modeling/qwen2_vl.py index a1370b04..35ab4325 100644 --- a/server/text_generation_server/models/custom_modeling/qwen2_vl.py +++ b/server/text_generation_server/models/custom_modeling/qwen2_vl.py @@ -14,7 +14,7 @@ # limitations under the License. """PyTorch Qwen2 VL model.""" -from typing import Dict, Optional, Tuple, List +from typing import Optional, Tuple, List import torch import torch.utils.checkpoint