Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)

Co-authored-by: SangBin Cho <rkooo567@gmail.com>
Co-authored-by: dhou-xai <dhou@x.ai>
Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>
This commit is contained in:
Lianmin Zheng
2025-03-03 00:12:04 -08:00
parent 0194948fd9
commit ac2387279e
86 changed files with 4116 additions and 2015 deletions

View File

@@ -210,8 +210,7 @@
"response = requests.post(url, json=data)\n",
"print_highlight(response.text)\n",
"assert response.json()[\"success\"] is True\n",
"assert response.json()[\"message\"] == \"Succeeded to update model weights.\"\n",
"assert response.json().keys() == {\"success\", \"message\"}"
"assert response.json()[\"message\"] == \"Succeeded to update model weights.\""
]
},
{
@@ -411,7 +410,7 @@
" },\n",
")\n",
"output = response.json()\n",
"output_tokens = output[\"token_ids\"]\n",
"output_tokens = output[\"output_ids\"]\n",
"\n",
"output_text = tokenizer.decode(output_tokens, skip_special_tokens=False)\n",
"print_highlight(f\"Tokenized Output: {output_tokens}\")\n",