vllm-project/compressed-tensors

[Bug] Unreachable GROUP+dynamic branch in QuantizationScheme.validate_model_after about 17 hours ago

bug good first issue question

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

[Refactor] Remove `g_idx == -1` checks 7 days ago

good first issue

vllm-project/compressed-tensors

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

[Bug] Disk Offloading and Deletion of Shared Tensors 15 days ago

bug good first issue

vllm-project/compressed-tensors

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

Write a guide for quantizing models using frameworks outside of Compressed-Tensors quantization about 1 month ago

documentation good first issue

vllm-project/compressed-tensors

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

[Performance] Speed up model loading by desynchronizing sync ops in `from_accelerate` about 1 month ago

good first issue

vllm-project/compressed-tensors

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

[convert] Add Converter for AutoAWQ format about 2 months ago

good first issue

vllm-project/compressed-tensors

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

[AssertionError] assert scale_dtype is torch.float32 in round_to_power_2 3 months ago

good first issue

vllm-project/compressed-tensors

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

Catch cpu mmap issues and create warning 3 months ago

good first issue

vllm-project/compressed-tensors

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

[Python 3.10+] Modernize codebase with Python 3.10+ idioms and features 5 months ago

enhancement good first issue keep-open

vllm-project/compressed-tensors

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

[Compressed Linear] Remove CompressedLinear 5 months ago

enhancement good first issue help wanted keep-open

vllm-project/compressed-tensors

294

A safetensors extension to efficiently store sparse quantized tensors on disk

Python

Open Issues Need Help