- 08 Dec, 2025 1 commit
-
-
laibao authored
-
- 05 Dec, 2025 1 commit
-
-
laibao authored
- 在 InputBatch.refresh_metadata 中为展开后的采样元数据引入 repeat_count 记录重复次数 - 完善元数据刷新逻辑以适配 reject-sampling 优化路径 - 更新 GPUModelRunnerBase，在 batch 处理阶段正确消费新的采样元数据与重复计数
-
- 04 Dec, 2025 5 commits
- 03 Dec, 2025 1 commit
-
-
zhuwenwen authored
-
- 02 Dec, 2025 9 commits
-
-
zhuwenwen authored
回退错误修改，避免dp模式漏掉的dispatch和combine通信 See merge request dcutoolkit/deeplearing/vllm!282
-
王敏 authored
-
王敏 authored
-
zhuwenwen authored
-
zhuwenwen authored
-
zhuwenwen authored
[fix]解决dp模式mtp卡住问题 See merge request dcutoolkit/deeplearing/vllm!280
-
王敏 authored
-
zhuwenwen authored
-
zhuwenwen authored
-
- 01 Dec, 2025 5 commits
- 28 Nov, 2025 2 commits
- 27 Nov, 2025 16 commits
-
-
zhuwenwen authored
-
zhuwenwen authored
解决宽松mtp request_ids报错找不到问题 See merge request dcutoolkit/deeplearing/vllm!276
-
王敏 authored
-
zhuwenwen authored
-
-
zhuwenwen authored
-
zhuwenwen authored
fix: moe quant bug and attention bug See merge request dcutoolkit/deeplearing/vllm!275
-
wujl5 authored
-
-
zhuwenwen authored
-
wujl5 authored
-
zhuwenwen authored
去掉宽松mtp中的隐式同步 See merge request dcutoolkit/deeplearing/vllm!274
-
王敏 authored
-
zhuwenwen authored
-
zhuwenwen authored
-
laibao authored
-
