gavindiaz/NexQuant
1
0
Fork 0
mirror of https://github.com/NicolasBohn/NexQuant.git synced 2026-07-27 23:47:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: skip Kronos factor on GPUs < 20GB to avoid CUDA OOM (shared with llama-server)

Browse Source
This commit is contained in:
TPTBusiness
2026-05-04 20:31:11 +02:00
parent c0ec1b39e1
commit 834cc686d1
1 changed files with 9 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
predix.py
+9 -2
View File
@@ -329,8 +329,15 @@ def quant(
threading.Thread(target=start_cli_dash, daemon=True).start()
time.sleep(1)
# ---- Kronos Factor: auto-generate if not in pool ----
_ensure_kronos_factor_in_pool(console)
# ---- Kronos Factor: skip if GPU unavailable (CUDA OOM with llama-server) ----
try:
import torch
if torch.cuda.is_available() and torch.cuda.get_device_properties(0).total_memory > 20 * 1024**3:
_ensure_kronos_factor_in_pool(console)
else:
console.print("[dim]Kronos Factor skipped — GPU < 20GB or CUDA unavailable[/dim]")
except Exception:
console.print("[dim]Kronos Factor skipped — torch not available[/dim]")
# ---- Start fin_quant ----
from rdagent.app.qlib_rd_loop.quant import main as fin_quant