Merge tag 'v0.5.2' into v0.5.2-dtk24.04.1

705f6a35 · zhuwenwen · af837396 · 4cf256ae · 705f6a35 · 705f6a35
Commit 705f6a35 authored Jul 16, 2024 by zhuwenwen
20 changed files
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json
--- 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/layernorm.py
+++ b/vllm/model_executor/layers/layernorm.py
--- a/vllm/model_executor/layers/linear.py
+++ b/vllm/model_executor/layers/linear.py
--- a/vllm/model_executor/layers/logits_processor.py
+++ b/vllm/model_executor/layers/logits_processor.py
--- a/vllm/model_executor/layers/quantization/awq.py
+++ b/vllm/model_executor/layers/quantization/awq.py
--- a/vllm/model_executor/layers/quantization/base_config.py
+++ b/vllm/model_executor/layers/quantization/base_config.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/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_scheme.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_unquantized.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_unquantized.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/schemes/compressed_tensors_w8a8_dynamictoken.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_dynamictoken.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py
--- a/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_statictensor.py
+++ b/vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_statictensor.py