open-webui

mirror of https://github.com/open-webui/open-webui.git synced 2026-07-10 04:20:44 +02:00

Files

G30 ee11069ef2 perf(ollama): offload multi-GB model file I/O with asyncio.to_thread (#25829 )

The Ollama model upload and download handlers perform three stages
of sync file I/O on multi-GB model files inside async handlers:

1. Persist upload — file.file.read() + write() in a loop
2. SHA-256 hash — calculate_sha256() reads the file sequentially
3. Read for blob push — open().read() loads entire model into memory

All three stages block the event loop for the duration of the I/O.
For a 4GB model, each stage freezes the event loop for 10+ seconds
while every other user's request stalls.

Wrap each blocking stage in asyncio.to_thread() in both handlers:

- upload_model(): persist upload, calculate_sha256, blob read
- download_file_stream(): calculate_sha256, blob read

Benchmark (full pipeline: write + SHA-256 + read back, 3 trials):
- 200MB: max jitter 145ms → 1ms (145x improvement)
- 500MB: max jitter 1,026ms → 1ms (1,026x improvement)

File I/O is pure I/O — no GIL contention. asyncio.to_thread()
completely eliminates event loop blocking.

2026-06-29 03:48:48 -05:00