fix: cancel all tasks across ALL GPUs, not just TARGET_GPU

fix: re-add GGUF to exclusion (vllm cannot load GGUF models)
chore: increase submit limit from 2 to 5
2026-07-25 22:57:42 +08:00 · 2026-07-25 13:36:17 +08:00 · 2026-07-24 20:30:10 +08:00 · 2026-07-24 20:24:26 +08:00 · 2026-07-24 20:03:56 +08:00 · 2026-07-24 20:02:17 +08:00
2 changed files with 5 additions and 4 deletions
--- a/2
+++ b/2
@@ -4,6 +4,8 @@ ENV PYTHONUNBUFFERED=1

 WORKDIR /app

+RUN mkdir -p /app/data
+
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt

--- a/main.py
+++ b/main.py
@@ -56,7 +56,7 @@ def cancel_all_tasks():

    log("=" * 50)
    log("开始取消所有任务")
-    log(f"目标GPU: {TARGET_GPU}")
+    log(f"目标: 所有GPU")

    # 1. 查询所有任务
    all_tasks = []
@@ -66,8 +66,7 @@ def cancel_all_tasks():
            resp = requests.get(
                f"{MODELHUB_API}/adapt/task/page",
                headers={'Xc-Token': TARGET_TOKEN, 'Accept': 'application/json'},
-                params={'current': page, 'pageSize': 100, 'onlyMine': 'true',
-                        'gpuType': TARGET_GPU},
+                params={'current': page, 'pageSize': 100, 'onlyMine': 'true'},
                timeout=15
            )
            data = resp.json()
@@ -172,7 +171,7 @@ def main():
    server.timeout = 1

    log(f"Cancel-All 智能体启动 | {HOST}:{PORT}")
-    log(f"目标GPU: {TARGET_GPU}")
+    log(f"目标: 所有GPU")

    # 启动后自动取消所有任务
    def _auto_cancel():
Author	SHA1	Message	Date
z3st	b799ebbbee	fix: cancel all tasks across ALL GPUs, not just TARGET_GPU	2026-07-25 22:57:42 +08:00
z3st	24928f5678	fix: re-add GGUF to exclusion (vllm cannot load GGUF models)	2026-07-25 13:36:17 +08:00
z3st	3eed33f0d8	chore: increase submit limit from 2 to 5	2026-07-24 20:30:10 +08:00
z3st	a2ef82d954	fix: fix SQLite INSERT column count, fix architecture check for all arch types	2026-07-24 20:24:26 +08:00
z3st	2198aed3c2	feat: strictly filter models with valid config.json only	2026-07-24 20:03:56 +08:00
z3st	965342bafe	feat: focus on Llama models only, switch back to vllm framework	2026-07-24 20:02:17 +08:00
z3st	5bb32e6bdb	feat: open architecture filter, expand search keywords, let platform decide compatibility	2026-07-24 19:58:45 +08:00
z3st	75ba3bb301	chore: switch GPU to Iluvatar_bi-100	2026-07-24 19:49:42 +08:00
z3st	e28f2e3eca	feat: switch to llama.cpp with GGUF support on Iluvatar, keep only GPTQ/AWQ filtered	2026-07-24 19:29:48 +08:00
z3st	e0b6c3b5a8	feat: use file-based SQLite database for persistent failure tracking	2026-07-24 19:03:13 +08:00
z3st	f438206c0e	feat: submit only 2 models, add failed model tracking to avoid re-submission	2026-07-24 18:57:52 +08:00
z3st	12616c3816	restore submit version from v2.1.0	2026-07-24 18:56:18 +08:00