EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

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

Browse Source 
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
Download Patch File Download Diff File Expand all files Collapse all files

2
test/srt/test_metrics.py
View File

@@ -56,11 +56,13 @@ class TestEnableMetrics(unittest.TestCase):
"sglang:gen_throughput",
"sglang:num_queue_reqs",
"sglang:cache_hit_rate",
"sglang:spec_accept_length",
"sglang:prompt_tokens_total",
"sglang:generation_tokens_total",
"sglang:num_requests_total",
"sglang:time_to_first_token_seconds",
"sglang:time_per_output_token_seconds",
"sglang:inter_token_latency_seconds",
"sglang:e2e_request_latency_seconds",
]