ChatGPT Optimierung / Korrektur

This commit is contained in:
Marc Blatter 2026-07-26 17:53:45 +00:00
parent c117a5561d
commit d080f54087
1 changed files with 1 additions and 1 deletions

View File

@ -25,7 +25,7 @@ services:
- --port=8005
- --quantization=awq
- --tensor-parallel-size=2
- --gpu-memory-utilization=0.84
- --gpu-memory-utilization=0.86
- --max-model-len=65536
- --hf-overrides={"rope_scaling":{"rope_type":"yarn","factor":2.0,"original_max_position_embeddings":32768}}
- --max-num-seqs=4