Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: remove unused deps and imports

This commit is contained in:
David Holtz 2024-11-18 21:48:09 +00:00
parent e428a14d19
commit 0fd2ab3e89
5 changed files with 11 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
docs/source/reference/launcher.md
View File

@ -62,15 +62,16 @@ Options:
[env: QUANTIZE=]
Possible values:
- awq: 4 bit quantization. Requires a specific AWQ quantized model: <https://hf.co/models?search=awq>. 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 <https://github.com/NetEase-FuXi/EETQ.git>
- exl2: Variable bit quantization. Requires a specific EXL2 quantized model: <https://hf.co/models?search=exl2>. Requires exllama2 kernels and does not support tensor parallelism (num_shard > 1)
- gptq: 4 bit quantization. Requires a specific GTPQ quantized model: <https://hf.co/models?search=gptq>. 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: <https://hf.co/models?search=marlin>
- 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: <https://hf.co/models?search=awq>. 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 <https://github.com/NetEase-FuXi/EETQ.git>
- exl2: Variable bit quantization. Requires a specific EXL2 quantized model: <https://hf.co/models?search=exl2>. Requires exllama2 kernels and does not support tensor parallelism (num_shard > 1)
- gptq: 4 bit quantization. Requires a specific GTPQ quantized model: <https://hf.co/models?search=gptq>. 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: <https://hf.co/models?search=marlin>
- 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

1
server/requirements_cuda.txt
View File

@ -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"

1
server/requirements_intel.txt
View File

@ -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"

1
server/requirements_rocm.txt
View File

@ -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"

2
server/text_generation_server/models/custom_modeling/qwen2_vl.py
View File

@ -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