tune for 1 orchestrator + up to 3 subagents: gpu-mem 0.88 (~15GB reserve), seqs=4, ctx 262144; document use case + tradeoffs
This commit is contained in:
@@ -8,7 +8,7 @@ NSPEC="${1:-2}"
|
||||
BACKEND="${2:-flash_attn}"
|
||||
MODEL="${MODEL:-Intel/Qwen3.5-122B-A10B-int4-AutoRound}"
|
||||
MAX_MODEL_LEN="${MAX_MODEL_LEN:-262144}"
|
||||
GPU_MEM="${GPU_MEM:-0.89}"
|
||||
GPU_MEM="${GPU_MEM:-0.88}"
|
||||
MAX_NUM_SEQS="${MAX_NUM_SEQS:-4}"
|
||||
MAX_BATCHED_TOKENS="${MAX_BATCHED_TOKENS:-8192}"
|
||||
PORT="${PORT:-8000}"
|
||||
|
||||
Reference in New Issue
Block a user