Sync v2.0 version of code to github repo

2026-04-23 17:11:21 +08:00 · 2025-06-29 23:29:37 +00:00
parent d151496038
commit 92c2cfa2e7
597 changed files with 78776 additions and 22905 deletions
@@ -0,0 +1,8 @@
+enable_chunked_prefill: True
+max_model_len: 131072
+max_num_seqs: 16
+kv_cache_ratio: 0.75
+tensor_parallel_size: 8
+max_num_batched_tokens: 4096
+max_num_partial_prefills: 3
+max_long_partial_prefills: 3