add inversion fallback

Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>

Author: kylesayrs

src/llmcompressor/modifiers/quantization/gptq/gptq_quantize.py

@@ -10,6 +10,7 @@
     QuantizationStrategy,
     fake_quantize,
 )
+from loguru import logger
 
 from llmcompressor.modifiers.utils import SPARSITY_THRESHOLD
 from llmcompressor.observers.base import Observer
@@ -161,11 +162,12 @@ def quantize_weight(
         H = torch.linalg.cholesky(H, upper=True)
         Hinv = H
     except torch._C._LinAlgError:
-        raise torch._C._LinAlgError(
+        logger.warning(
             "Failed to invert hessian due to numerical instability. Consider "
             "increasing GPTQModifier.dampening_frac, increasing the number "
             "of calibration samples, or shuffling the calibration dataset"
         )
+        Hinv = H = torch.eye(num_columns, dtype=H.dtype, device=H.device)
 
     # See section 3.4 of https://arxiv.org/abs/2203.07259
     for i1 in range(0, num_columns, blocksize):