Update to new version of base image

2025-10-24 15:45:06 +08:00
parent ee04aead1e
commit fad74b701b
476 changed files with 1270 additions and 46 deletions
--- a/vllm/model_executor/layers/quantization/pycache/init.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/init.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/aqlm.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/aqlm.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/awq.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/awq.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/awq_marlin.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/awq_marlin.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/awq_triton.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/awq_triton.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/base_config.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/base_config.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/bitsandbytes.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/bitsandbytes.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/deepspeedfp.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/deepspeedfp.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/experts_int8.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/experts_int8.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/fbgemm_fp8.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/fbgemm_fp8.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/fp8.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/fp8.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/gguf.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/gguf.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/gptq.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/gptq.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/gptq_marlin.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/gptq_marlin.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/gptq_marlin_24.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/gptq_marlin_24.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/ipex_quant.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/ipex_quant.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/kv_cache.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/kv_cache.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/marlin.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/marlin.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/modelopt.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/modelopt.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/neuron_quant.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/neuron_quant.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/qqq.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/qqq.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/schema.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/schema.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/tpu_int8.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/tpu_int8.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/pycache/w8a16.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/pycache/w8a16.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/pycache/init.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/pycache/init.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/pycache/compressed_tensors.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/pycache/compressed_tensors.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/pycache/compressed_tensors_moe.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/pycache/compressed_tensors_moe.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/pycache/utils.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/pycache/utils.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/init.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/init.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_scheme.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_scheme.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_w4a16_24.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_w4a16_24.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_w8a16_fp8.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_w8a16_fp8.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_w8a8_fp8.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_w8a8_fp8.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_w8a8_int8.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_w8a8_int8.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_wNa16.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/pycache/compressed_tensors_wNa16.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/compressed_tensors/utils.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/utils.py
@@ -1,4 +1,4 @@
-import re
+import regex as re
 from enum import Enum
 from typing import Any, Dict, Iterable, Optional, Union

--- a/vllm/model_executor/layers/quantization/kernels/pycache/MPLinearKernel.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/kernels/pycache/MPLinearKernel.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/kernels/pycache/init.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/kernels/pycache/init.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/kernels/pycache/machete.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/kernels/pycache/machete.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/kernels/pycache/marlin.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/kernels/pycache/marlin.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/init.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/init.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/layer_utils.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/layer_utils.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/machete_utils.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/machete_utils.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils_fp8.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils_fp8.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils_test.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils_test.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils_test_24.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils_test_24.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils_test_qqq.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/marlin_utils_test_qqq.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/quant_utils.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/quant_utils.cpython-310.pyc
--- a/vllm/model_executor/layers/quantization/utils/pycache/w8a8_utils.cpython-310.pyc
+++ b/vllm/model_executor/layers/quantization/utils/pycache/w8a8_utils.cpython-310.pyc