Merge tag 'v0.7.2' into v0.7.2-dev

66b809cc · zhuwenwen · 37b63c24 · 0408efc6 · 66b809cc · 66b809cc
Commit 66b809cc authored Feb 08, 2025 by zhuwenwen
20 changed files
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
+++ b/vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json
--- a/vllm/model_executor/layers/quantization/utils/fp8_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/fp8_utils.py
--- a/vllm/model_executor/layers/quantization/utils/layer_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/layer_utils.py
--- a/vllm/model_executor/layers/quantization/utils/machete_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/machete_utils.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_test.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_test.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py
--- a/vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py
+++ b/vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py
--- a/vllm/model_executor/layers/quantization/utils/quant_utils.py
+++ b/vllm/model_executor/layers/quantization/utils/quant_utils.py