Sync v2.0 version of code to github repo

This commit is contained in:
Jiang-Jia-Jun
2025-06-29 23:29:37 +00:00
parent d151496038
commit 92c2cfa2e7
597 changed files with 78776 additions and 22905 deletions

View File

@@ -0,0 +1,6 @@
max_model_len: 32768
max_num_seqs: 256
gpu_memory_utilization: 0.9
kv_cache_ratio: 0.75
quantization: wint8
tensor_parallel_size: 1