SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

add xpu path for awq (#34712)

Browse Source 
* add xpu path for awq

* update readme
This commit is contained in:
jiqing-feng
2024-11-15 22:45:24 +08:00
committed by GitHub
parent 7b3d615bc2
commit 52ea4aa589
2 changed files with 20 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
docs/source/en/quantization/overview.md
View File

@@ -45,19 +45,19 @@ In short, supporting a wide range of quantization methods allows you to pick the
Use the table below to help you decide which quantization method to use. Use the table below to help you decide which quantization method to use.
| Quantization method | On the fly quantization | CPU | CUDA GPU | RoCm GPU (AMD) | Metal (Apple Silicon) | torch.compile() support | Number of bits | Supports fine-tuning (through PEFT) | Serializable with 🤗 transformers | 🤗 transformers support | Link to library | | Quantization method | On the fly quantization | CPU | CUDA GPU | RoCm GPU (AMD) | Metal (Apple Silicon) | Intel GPU | torch.compile() support | Number of bits | Supports fine-tuning (through PEFT) | Serializable with 🤗 transformers | 🤗 transformers support | Link to library |
|-------------------------------------|-------------------------|-----|----------|----------------|-----------------------|-------------------------|----------------|-------------------------------------|--------------|------------------------|---------------------------------------------| |-------------------------------------|-------------------------|-----|----------|----------------|-----------------------|-----------|-------------------------|----------------|-------------------------------------|--------------|------------------------|---------------------------------------------|
| [AQLM](./aqlm) | 🔴 | 🟢 | 🟢 | 🔴 | 🔴 | 🟢 | 1 / 2 | 🟢 | 🟢 | 🟢 | https://github.com/Vahe1994/AQLM | | [AQLM](./aqlm) | 🔴 | 🟢 | 🟢 | 🔴 | 🔴 | 🔴 | 🟢 | 1 / 2 | 🟢 | 🟢 | 🟢 | https://github.com/Vahe1994/AQLM |
| [AWQ](./awq) | 🔴 | 🔴 | 🟢 | 🟢 | 🔴 | ? | 4 | 🟢 | 🟢 | 🟢 | https://github.com/casper-hansen/AutoAWQ | | [AWQ](./awq) | 🔴 | 🟢 | 🟢 | 🟢 | 🔴 | 🟢 | ? | 4 | 🟢 | 🟢 | 🟢 | https://github.com/casper-hansen/AutoAWQ |
| [bitsandbytes](./bitsandbytes) | 🟢 | 🟡 * | 🟢 | 🟡 * | 🔴 ** | 🔴 (soon!) | 4 / 8 | 🟢 | 🟢 | 🟢 | https://github.com/bitsandbytes-foundation/bitsandbytes | | [bitsandbytes](./bitsandbytes) | 🟢 | 🟡 * | 🟢 | 🟡 * | 🔴 ** | 🟡 * | 🔴 (soon!) | 4 / 8 | 🟢 | 🟢 | 🟢 | https://github.com/bitsandbytes-foundation/bitsandbytes |
| [compressed-tensors](./compressed_tensors) | 🔴 | 🟢 | 🟢 | 🟢 | 🔴 | 🔴 | 1 - 8 | 🟢 | 🟢 | 🟢 | https://github.com/neuralmagic/compressed-tensors | | [compressed-tensors](./compressed_tensors) | 🔴 | 🟢 | 🟢 | 🟢 | 🔴 | 🔴 | 🔴 | 1 - 8 | 🟢 | 🟢 | 🟢 | https://github.com/neuralmagic/compressed-tensors |
| [EETQ](./eetq) | 🟢 | 🔴 | 🟢 | 🔴 | 🔴 | ? | 8 | 🟢 | 🟢 | 🟢 | https://github.com/NetEase-FuXi/EETQ | | [EETQ](./eetq) | 🟢 | 🔴 | 🟢 | 🔴 | 🔴 | 🔴 | ? | 8 | 🟢 | 🟢 | 🟢 | https://github.com/NetEase-FuXi/EETQ |
| GGUF / GGML (llama.cpp) | 🟢 | 🟢 | 🟢 | 🔴 | 🟢 | 🔴 | 1 - 8 | 🔴 | [See GGUF section](../gguf) | [See GGUF section](../gguf) | https://github.com/ggerganov/llama.cpp | | GGUF / GGML (llama.cpp) | 🟢 | 🟢 | 🟢 | 🔴 | 🟢 | 🔴 | 🔴 | 1 - 8 | 🔴 | [See GGUF section](../gguf) | [See GGUF section](../gguf) | https://github.com/ggerganov/llama.cpp |
| [GPTQ](./gptq) | 🔴 | 🔴 | 🟢 | 🟢 | 🔴 | 🔴 | 2 - 3 - 4 - 8 | 🟢 | 🟢 | 🟢 | https://github.com/AutoGPTQ/AutoGPTQ | | [GPTQ](./gptq) | 🔴 | 🔴 | 🟢 | 🟢 | 🔴 | 🔴 | 🔴 | 2 - 3 - 4 - 8 | 🟢 | 🟢 | 🟢 | https://github.com/AutoGPTQ/AutoGPTQ |
| [HQQ](./hqq) | 🟢 | 🟢 | 🟢 | 🔴 | 🔴 | 🟢 | 1 - 8 | 🟢 | 🔴 | 🟢 | https://github.com/mobiusml/hqq/ | | [HQQ](./hqq) | 🟢 | 🟢 | 🟢 | 🔴 | 🔴 | 🔴 | 🟢 | 1 - 8 | 🟢 | 🔴 | 🟢 | https://github.com/mobiusml/hqq/ |
| [Quanto](./quanto) | 🟢 | 🟢 | 🟢 | 🔴 | 🟢 | 🟢 | 2 / 4 / 8 | 🔴 | 🔴 | 🟢 | https://github.com/huggingface/quanto | | [Quanto](./quanto) | 🟢 | 🟢 | 🟢 | 🔴 | 🟢 | 🔴 | 🟢 | 2 / 4 / 8 | 🔴 | 🔴 | 🟢 | https://github.com/huggingface/quanto |
| [FBGEMM_FP8](./fbgemm_fp8.md) | 🟢 | 🔴 | 🟢 | 🔴 | 🔴 | 🔴 | 8 | 🔴 | 🟢 | 🟢 | https://github.com/pytorch/FBGEMM | | [FBGEMM_FP8](./fbgemm_fp8.md) | 🟢 | 🔴 | 🟢 | 🔴 | 🔴 | 🔴 | 🔴 | 8 | 🔴 | 🟢 | 🟢 | https://github.com/pytorch/FBGEMM |
| [torchao](./torchao.md) | 🟢 | | 🟢 | 🔴 | partial support (int4 weight only) | | 4 / 8 | | 🟢🔴 | 🟢 | https://github.com/pytorch/ao | | [torchao](./torchao.md) | 🟢 | | 🟢 | 🔴 | partial support (int4 weight only) | 🔴 | | 4 / 8 | | 🟢🔴 | 🟢 | https://github.com/pytorch/ao |
<Tip> <Tip>

14
src/transformers/quantizers/quantizer_awq.py
View File

@@ -57,14 +57,14 @@ class AwqQuantizer(HfQuantizer):
raise RuntimeError( raise RuntimeError(
"To use IPEX backend, you need autoawq>0.6.2. Please install the latest version or from source." "To use IPEX backend, you need autoawq>0.6.2. Please install the latest version or from source."
) )
if ( if device_map is None:
device_map is not None logger.warning_once(
and isinstance(device_map, dict) "You have loaded an AWQ model without setting device_map, please set 'cpu' or 'xpu' or 'auto'"
and (torch.device("cpu") not in device_map.values() or len(device_map.values()) > 1) )
): elif isinstance(device_map, dict) and "disk" in device_map.values():
raise ValueError( raise ValueError(
"You are attempting to load an IPEX version AWQ model with a device_map that contains more than CPU." "You are attempting to load an IPEX version AWQ model with a device_map that contains disk device."
" This is not supported. Please make sure only cpu in the device_map." " This is not supported. Please make sure only cpu and xpu in the device_map."
) )
else: else:
if not torch.cuda.is_available(): if not torch.cuda.is_available():