Merge tag 'v0.6.6.post1' into v0.6.6.post1-dev

96ae75ad · zhuwenwen · f9f4a735 · 2339d59f · 96ae75ad · 96ae75ad
Commit 96ae75ad authored Jan 04, 2025 by zhuwenwen
20 changed files
--- a/vllm/lora/models.py
+++ b/vllm/lora/models.py
--- a/vllm/lora/utils.py
+++ b/vllm/lora/utils.py
--- a/vllm/lora/worker_manager.py
+++ b/vllm/lora/worker_manager.py
--- a/vllm/model_executor/guided_decoding/__init__.py
+++ b/vllm/model_executor/guided_decoding/__init__.py
--- a/vllm/model_executor/guided_decoding/outlines_logits_processors.py
+++ b/vllm/model_executor/guided_decoding/outlines_logits_processors.py
--- a/vllm/model_executor/guided_decoding/xgrammar_utils.py
+++ b/vllm/model_executor/guided_decoding/xgrammar_utils.py
--- a/vllm/model_executor/guided_decoding/xgrammar_decoding.py
+++ b/vllm/model_executor/guided_decoding/xgrammar_decoding.py
--- a/vllm/model_executor/layers/fused_moe/fused_moe.py
+++ b/vllm/model_executor/layers/fused_moe/fused_moe.py
--- a/vllm/model_executor/layers/fused_moe/layer.py
+++ b/vllm/model_executor/layers/fused_moe/layer.py
--- a/vllm/model_executor/layers/linear.py
+++ b/vllm/model_executor/layers/linear.py
--- a/vllm/model_executor/layers/quantization/awq_marlin.py
+++ b/vllm/model_executor/layers/quantization/awq_marlin.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/__init__.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/utils.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/utils.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/gptq_marlin.py
+++ b/vllm/model_executor/layers/quantization/gptq_marlin.py