r1.9.0

wang_shaocong1. ds-r1 ep and add ut/st

01aaed17创建于 2025年5月30日历史提交

文件	最后提交记录	最后更新时间
predict_deepseek_r1_671b.yaml	deepseek v3/r1 and qwen support chunked prefill and prefix caching, kvcache input	1 年前
predict_deepseek_r1_671b_w8a8.yaml	1. ds-r1 ep and add ut/st 2. mtp support 0.8.3 3. remove pynative judgement for the unit of eager mode and graph mode	11 个月前
predict_deepseek_r1_671b_w8a8_ep16.yaml	1. ds-r1 ep and add ut/st 2. mtp support 0.8.3 3. remove pynative judgement for the unit of eager mode and graph mode	11 个月前
predict_deepseek_r1_671b_w8a8_ep4tp4.yaml	1. ds-r1 ep and add ut/st 2. mtp support 0.8.3 3. remove pynative judgement for the unit of eager mode and graph mode	11 个月前