Merge tag 'v0.7.3' into v0.7.3-dev

ec5e299c · zhuwenwen · 47bd229c · ed6e9075 · ec5e299c · ec5e299c
Commit ec5e299c authored Feb 21, 2025 by zhuwenwen
20 changed files
--- 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/utils.py
+++ b/vllm/model_executor/guided_decoding/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/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
--- a/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.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=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
+++ b/vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json