project6-dev f1a408c75f fix: cap default_max_tokens at 8192 — prevent OOM kill on unlimited generation ...

t3_max_tokens_none test sends request without max_tokens.
With max_model_len=262144, default_max_tokens was ~260K tokens.
Model generates indefinitely at 12 TPS, container gets OOM killed after ~6min.
Cap at 8192 prevents memory exhaustion while still allowing long outputs.

2026-08-12 04:06:21 +00:00

qwen3_6_scripts

fix: cap default_max_tokens at 8192 — prevent OOM kill on unlimited generation

2026-08-12 04:06:21 +00:00

computility-run.yaml

fix: max-num-seqs=2 — t2_n_2测试需要n=2多路生成

2026-08-12 03:58:20 +00:00

Dockerfile

wudixzy stack docker build test: 2615-line qwen3_5.py + 12 prebuilt .so + 251-line patch_ops.sh

2026-08-12 03:17:31 +00:00

Description

No description provided

15 MiB

Languages

Python 88.5%

Cuda 9.2%

Shell 2.3%