kvcache-ai-ktransformers/ktransformers/server
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
..
api [update] support openai chat completion api 2025-03-07 08:51:09 +00:00
backend prevent rpc process from crashing on long prompt 2025-04-13 16:13:16 +08:00
balance_serve format kvc2, delete quant_configs, move model_configs to ~/.ktransformers 2025-04-08 10:06:07 +00:00
config format kvc2, delete quant_configs, move model_configs to ~/.ktransformers 2025-04-08 10:06:07 +00:00
crud Initial commit 2024-07-27 16:06:58 +08:00
models Initial commit 2024-07-27 16:06:58 +08:00
schemas add balance-serve, support concurrence 2025-03-31 22:55:32 +08:00
utils add balance-serve, support concurrence 2025-03-31 22:55:32 +08:00
__init__.py Initial commit 2024-07-27 16:06:58 +08:00
args.py format kvc2, delete quant_configs, move model_configs to ~/.ktransformers 2025-04-08 10:06:07 +00:00
exceptions.py Initial commit 2024-07-27 16:06:58 +08:00
main.py add balance-serve, support concurrence 2025-03-31 22:55:32 +08:00
requirements.txt add balance-serve, support concurrence 2025-03-31 22:55:32 +08:00