From 70e132244a61425a6b88c0b8345e496dc5bdfecd Mon Sep 17 00:00:00 2001
From: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Date: Fri, 28 Mar 2025 09:30:08 -0700
Subject: [PATCH] [Minor] Remove TGI launching script  (#15646)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
---
 benchmarks/benchmark_serving.py                  |  3 ---
 .../benchmark_serving_structured_output.py       |  3 ---
 benchmarks/launch_tgi_server.sh                  | 16 ----------------
 3 files changed, 22 deletions(-)
 delete mode 100755 benchmarks/launch_tgi_server.sh

diff --git a/benchmarks/benchmark_serving.py b/benchmarks/benchmark_serving.py
index 82c6b426b9a2b..e2f712dfc6f49 100644
--- a/benchmarks/benchmark_serving.py
+++ b/benchmarks/benchmark_serving.py
@@ -7,9 +7,6 @@ On the server side, run one of the following commands:
         --swap-space 16 \
         --disable-log-requests
 
-    (TGI backend)
-    ./launch_tgi_server.sh <your_model> <max_batch_total_tokens>
-
 On the client side, run:
     python benchmarks/benchmark_serving.py \
         --backend <backend> \
diff --git a/benchmarks/benchmark_serving_structured_output.py b/benchmarks/benchmark_serving_structured_output.py
index c79a93faff197..71cb420a52c46 100644
--- a/benchmarks/benchmark_serving_structured_output.py
+++ b/benchmarks/benchmark_serving_structured_output.py
@@ -5,9 +5,6 @@ On the server side, run one of the following commands:
     (vLLM OpenAI API server)
     vllm serve <your_model> --disable-log-requests
 
-    (TGI backend)
-    ./launch_tgi_server.sh <your_model> <max_batch_total_tokens>
-
 On the client side, run:
     python benchmarks/benchmark_serving_structured_output.py \
         --backend <backend> \
diff --git a/benchmarks/launch_tgi_server.sh b/benchmarks/launch_tgi_server.sh
deleted file mode 100755
index ba7383d88dc49..0000000000000
--- a/benchmarks/launch_tgi_server.sh
+++ /dev/null
@@ -1,16 +0,0 @@
-#!/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"