Skip to content

add xpu path for awq #34712

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Nov 15, 2024
Merged

add xpu path for awq #34712

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4a08c62
add xpu path for awq
jiqing-feng Nov 11, 2024
c7fd5df
Merge branch 'main' into awq_xpu
jiqing-feng Nov 13, 2024
d2c5bfb
Merge branch 'main' into awq_xpu
jiqing-feng Nov 15, 2024
96e6764
update readme
jiqing-feng Nov 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 13 additions & 13 deletions docs/source/en/quantization/overview.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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.

| 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 |
|-------------------------------------|-------------------------|-----|----------|----------------|-----------------------|-------------------------|----------------|-------------------------------------|--------------|------------------------|---------------------------------------------|
| [AQLM](./aqlm) | 🔴 | 🟢 | 🟢 | 🔴 | 🔴 | 🟢 | 1 / 2 | 🟢 | 🟢 | 🟢 | https://github.com/Vahe1994/AQLM |
| [AWQ](./awq) | 🔴 | 🔴 | 🟢 | 🟢 | 🔴 | ? | 4 | 🟢 | 🟢 | 🟢 | https://github.com/casper-hansen/AutoAWQ |
| [bitsandbytes](./bitsandbytes) | 🟢 | 🟡 * | 🟢 | 🟡 * | 🔴 ** | 🔴 (soon!) | 4 / 8 | 🟢 | 🟢 | 🟢 | https://github.com/bitsandbytes-foundation/bitsandbytes |
| [compressed-tensors](./compressed_tensors) | 🔴 | 🟢 | 🟢 | 🟢 | 🔴 | 🔴 | 1 - 8 | 🟢 | 🟢 | 🟢 | https://github.com/neuralmagic/compressed-tensors |
| [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 |
| [GPTQ](./gptq) | 🔴 | 🔴 | 🟢 | 🟢 | 🔴 | 🔴 | 2 - 3 - 4 - 8 | 🟢 | 🟢 | 🟢 | https://github.com/AutoGPTQ/AutoGPTQ |
| [HQQ](./hqq) | 🟢 | 🟢 | 🟢 | 🔴 | 🔴 | 🟢 | 1 - 8 | 🟢 | 🔴 | 🟢 | https://github.com/mobiusml/hqq/ |
| [Quanto](./quanto) | 🟢 | 🟢 | 🟢 | 🔴 | 🟢 | 🟢 | 2 / 4 / 8 | 🔴 | 🔴 | 🟢 | https://github.com/huggingface/quanto |
| [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 |
| 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 |
| [AWQ](./awq) | 🔴 | 🟢 | 🟢 | 🟢 | 🔴 | 🟢 | ? | 4 | 🟢 | 🟢 | 🟢 | https://github.com/casper-hansen/AutoAWQ |
| [bitsandbytes](./bitsandbytes) | 🟢 | 🟡 * | 🟢 | 🟡 * | 🔴 ** | 🟡 * | 🔴 (soon!) | 4 / 8 | 🟢 | 🟢 | 🟢 | https://github.com/bitsandbytes-foundation/bitsandbytes |
| [compressed-tensors](./compressed_tensors) | 🔴 | 🟢 | 🟢 | 🟢 | 🔴 | 🔴 | 🔴 | 1 - 8 | 🟢 | 🟢 | 🟢 | https://github.com/neuralmagic/compressed-tensors |
| [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 |
| [GPTQ](./gptq) | 🔴 | 🔴 | 🟢 | 🟢 | 🔴 | 🔴 | 🔴 | 2 - 3 - 4 - 8 | 🟢 | 🟢 | 🟢 | https://github.com/AutoGPTQ/AutoGPTQ |
| [HQQ](./hqq) | 🟢 | 🟢 | 🟢 | 🔴 | 🔴 | 🔴 | 🟢 | 1 - 8 | 🟢 | 🔴 | 🟢 | https://github.com/mobiusml/hqq/ |
| [Quanto](./quanto) | 🟢 | 🟢 | 🟢 | 🔴 | 🟢 | 🔴 | 🟢 | 2 / 4 / 8 | 🔴 | 🔴 | 🟢 | https://github.com/huggingface/quanto |
| [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 |

<Tip>

Expand Down
14 changes: 7 additions & 7 deletions src/transformers/quantizers/quantizer_awq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,14 +57,14 @@ def validate_environment(self, device_map, **kwargs):
raise RuntimeError(
"To use IPEX backend, you need autoawq>0.6.2. Please install the latest version or from source."
)
if (
device_map is not None
and isinstance(device_map, dict)
and (torch.device("cpu") not in device_map.values() or len(device_map.values()) > 1)
):
if device_map is None:
logger.warning_once(
"You have loaded an AWQ model without setting device_map, please set 'cpu' or 'xpu' or 'auto'"
)
elif isinstance(device_map, dict) and "disk" in device_map.values():
raise ValueError(
"You are attempting to load an IPEX version AWQ model with a device_map that contains more than CPU."
" This is not supported. Please make sure only cpu in the device_map."
"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 and xpu in the device_map."
)
else:
if not torch.cuda.is_available():
Expand Down
Loading