Sync v2.0 version of code to github repo

2026-04-24 01:29:57 +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 +1,11 @@
+max_model_len: 32768
+max_num_seqs: 256
+tensor_parallel_size: 8
+gpu_memory_utilization: 0.9
+kv_cache_ratio: 0.8
+enable_chunked_prefill: True
+max_num_batched_tokens: 1024
+max_num_partial_prefills: 3
+max_long_partial_prefills: 3
+enable_prefix_caching: True
+swap_space: 200