kvcache-ai-ktransformers/ktransformers/server/backend/interfaces
wangkuigang-yewu-cmss 4538bdae97 prevent rpc process from crashing on long prompt
当prompt超过cache_len的时候,rpc进程会crash掉,导致整体不可用。
这里增加一个检查,让过长的prompt在请求早期就被提前过滤掉
2025-04-13 16:13:16 +08:00
..
__init__.py Initial commit 2024-07-27 16:06:58 +08:00
balance_serve.py prevent rpc process from crashing on long prompt 2025-04-13 16:13:16 +08:00
exllamav2.py Initial commit 2024-07-27 16:06:58 +08:00
ktransformers.py add balance-serve, support concurrence 2025-03-31 22:55:32 +08:00
transformers.py fix top_p = 0 bug 2025-04-01 20:38:33 +08:00