Update benchmarks to use HF token from environment. (#15421)

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

benchmark/hicache/data_processing.py

@@ -11,10 +11,10 @@ from nextqa import NExTQALoader
 from tqdm.asyncio import tqdm
 from transformers import PreTrainedTokenizerBase
 
-SHAREGPT_URL = "https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json"
-
 from sglang.bench_serving import (
-    download_and_cache_file,
+    SHAREGPT_FILENAME,
+    SHAREGPT_REPO_ID,
+    download_and_cache_hf_file,
     gen_prompt,
     get_gen_prefix_cache_path,
 )
@@ -104,7 +104,10 @@ def sample_sharegpt_requests(
 
     # Download sharegpt if necessary
     if not os.path.isfile(dataset_path):
-        dataset_path = download_and_cache_file(SHAREGPT_URL)
+        dataset_path = download_and_cache_hf_file(
+            repo_id=SHAREGPT_REPO_ID,
+            filename=SHAREGPT_FILENAME,
+        )
 
     # Load the dataset.
     with open(dataset_path) as f:
@@ -367,7 +370,10 @@ def sample_random_requests(
 
         # Download sharegpt if necessary
         if not os.path.isfile(dataset_path):
-            dataset_path = download_and_cache_file(SHAREGPT_URL)
+            dataset_path = download_and_cache_hf_file(
+                repo_id=SHAREGPT_REPO_ID,
+                filename=SHAREGPT_FILENAME,
+            )
 
         # Load the dataset.
         with open(dataset_path) as f: