default max-num-seqs=4 (>=2 with headroom; ~5 fit full native ctx each)

2026-06-24 13:21:52 +10:00
parent 7dd6a74d38
commit 6797a9f6dd
4 changed files with 5 additions and 5 deletions
@@ -21,7 +21,7 @@ MODEL="${MODEL:-Intel/Qwen3.5-122B-A10B-int4-AutoRound}"
 DRAFT="${DRAFT:-z-lab/Qwen3.5-122B-A10B-DFlash}"
 MAX_MODEL_LEN="${MAX_MODEL_LEN:-262144}"      # model native max; KV is ~24 KiB/token so it fits
 GPU_MEM="${GPU_MEM:-0.89}"                     # ~14 GB reserved on a 128 GB (119 GiB) GB10
-MAX_NUM_SEQS="${MAX_NUM_SEQS:-1}"             # single-stream; each seq also reserves GDN state
+MAX_NUM_SEQS="${MAX_NUM_SEQS:-4}"             # ~5 seqs fit the full native ctx each (KV pool ~1.38M / 262144)
 MAX_BATCHED_TOKENS="${MAX_BATCHED_TOKENS:-8192}"  # chunked-prefill chunk (NOT = max-model-len)
 PORT="${PORT:-8000}"