更新README.md，修改Docker镜像版本，调整环境变量格式，优化基准测试脚本，添加新的基准测试功能，删除不再使用的示例文件。

benchmarks/kernels/benchmark_shapes.py

+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+
 WEIGHT_SHAPES = {
     "ideal": [[4 * 256 * 32, 256 * 32]],
     "mistralai/Mistral-7B-v0.1/TP1": [
@@ -73,3 +76,19 @@ WEIGHT_SHAPES = {
         [7168, 8192],
     ],
 }
+
+WEIGHT_SHAPES_MOE = {
+    "nm-testing/Mixtral-8x7B-Instruct-v0.1": [
+        [8, 2, 4096, 28672],
+        [8, 2, 14336, 4096],
+    ],
+    "nm-testing/deepseekv2-lite": [
+        [64, 6, 2048, 1408],
+    ],
+    "ibm-granite/granite-3.0-1b-a400m": [
+        [32, 8, 1024, 1024],
+    ],
+    "ibm-granite/granite-3.0-3b-a800m": [
+        [40, 8, 1024, 1536],
+    ],
+}

benchmarks/launch_tgi_server.sh

-#!/bin/bash
-
-PORT=8000
-MODEL=$1
-TOKENS=$2
-
-docker run -e HF_TOKEN=$HF_TOKEN --gpus all --shm-size 1g -p $PORT:80 \
-           -v $PWD/data:/data \
-           ghcr.io/huggingface/text-generation-inference:2.2.0 \
-           --model-id $MODEL \
-           --sharded false  \
-           --max-input-length 1024 \
-           --max-total-tokens 2048 \
-           --max-best-of 5 \
-           --max-concurrent-requests 5000 \
-           --max-batch-total-tokens $TOKENS