Merge tag 'v0.9.2' into v0.9.2-ori

99324e25 · zhuwenwen · cc7f22a8 · a5dd03c1 · 99324e25 · 99324e25
Commit 99324e25 authored Jul 12, 2025 by zhuwenwen
20 changed files
--- a/vllm/model_executor/layers/quantization/base_config.py
+++ b/vllm/model_executor/layers/quantization/base_config.py
--- a/vllm/model_executor/layers/quantization/bitblas.py
+++ b/vllm/model_executor/layers/quantization/bitblas.py
--- a/vllm/model_executor/layers/quantization/bitsandbytes.py
+++ b/vllm/model_executor/layers/quantization/bitsandbytes.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py
--- a/vllm/model_executor/layers/quantization/deepgemm.py
+++ b/vllm/model_executor/layers/quantization/deepgemm.py
--- a/vllm/model_executor/layers/quantization/experts_int8.py
+++ b/vllm/model_executor/layers/quantization/experts_int8.py
--- a/vllm/model_executor/layers/quantization/fp8.py
+++ b/vllm/model_executor/layers/quantization/fp8.py
--- a/vllm/model_executor/layers/quantization/gguf.py
+++ b/vllm/model_executor/layers/quantization/gguf.py
--- a/vllm/model_executor/layers/quantization/gptq_bitblas.py
+++ b/vllm/model_executor/layers/quantization/gptq_bitblas.py
--- a/vllm/model_executor/layers/quantization/gptq_marlin.py
+++ b/vllm/model_executor/layers/quantization/gptq_marlin.py
--- a/vllm/model_executor/layers/quantization/ipex_quant.py
+++ b/vllm/model_executor/layers/quantization/ipex_quant.py
--- a/vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py
+++ b/vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py
--- a/vllm/model_executor/layers/quantization/marlin.py
+++ b/vllm/model_executor/layers/quantization/marlin.py
--- a/vllm/model_executor/layers/quantization/modelopt.py
+++ b/vllm/model_executor/layers/quantization/modelopt.py
--- a/vllm/model_executor/layers/quantization/moe_wna16.py
+++ b/vllm/model_executor/layers/quantization/moe_wna16.py
--- a/vllm/model_executor/layers/quantization/quark/quark.py
+++ b/vllm/model_executor/layers/quantization/quark/quark.py