Sync v2.0 version of code to github repo

2026-04-23 08:21:53 +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 +1,9 @@
+enable_prefix_caching: True
+max_model_len: 32768
+max_num_batched_tokens: 68304
+max_num_seqs: 128
+gpu_memory_utilization: 0.9
+kv_cache_ratio: 0.71
+tensor_parallel_size: 8
+swap_space: 100
+cache_queue_port: 55664