10 Commits

Author	SHA1	Message	Date
myhloli	bcb30fe79c	fix: simplify VRAM size retrieval and improve error handling in memory management	2025-12-01 18:31:07 +08:00
myhloli	44fdeb663f	Refactor async function and improve output directory handling in prediction	2025-10-13 11:32:28 +08:00
myhloli	3ec6479462	fix: update backend comment to reflect renaming from sglang-engine to vlm-vllm-engine	2025-09-15 02:00:58 +08:00
zhanluxianshen	1671e68367	fix error logs for multi_gpu endpoint. ... Signed-off-by: zhanluxianshen <zhanluxianshen@163.com>	2025-08-26 10:26:10 +08:00
Xiaomeng Zhao	d3f6736e0a	Update _config_endpoint.py	2025-07-05 04:33:49 +08:00
Xiaomeng Zhao	07b4cbc0ec	Update projects/multi_gpu_v2/_config_endpoint.py ... Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-07-05 04:32:31 +08:00
Xiaomeng Zhao	c08a86d6c7	Update projects/multi_gpu_v2/server.py ... Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2025-07-05 04:29:36 +08:00
Xiaomeng Zhao	ea9336c0c1	Update server.py	2025-07-05 04:14:58 +08:00
ca1yz	3f32f2a587	Update README.md	2025-06-18 19:08:39 +08:00
ca1yz	dbfd392f05	add updated example project based on 2.0	2025-06-18 19:07:53 +08:00