From 55d5a4c416855d0b022196ac389b12d64bfcd63d Mon Sep 17 00:00:00 2001 From: SZCJW <792430652@qq.com> Date: Sun, 29 Mar 2026 00:29:54 +0800 Subject: [PATCH] x --- config.json | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/config.json b/config.json index a65f371..c88c4fc 100644 --- a/config.json +++ b/config.json @@ -29,12 +29,12 @@ "hf_model_id": "RedHatAI/Qwen3-14B-FP8-dynamic" }, "Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit": { - "ctx": "24576", + "ctx": "131072", // 128K "trust_remote": true, "valid_tp": [1, 2], - "max_num_seqs": "64", - "max_tokens": "32768", - "gpu_util": "0.98", + "max_num_seqs": "32", // 适当减少以节省显存 + "max_tokens": "65536", + "gpu_util": "0.95", // 适当降低以预留更多显存 "hf_model_id": "cpatonn/Qwen3-Coder-30B-A3B-Instruct-GPTQ-4bit" }, "Qwen3-Next-80B-A3B-Instruct-AWQ-4bit": {