- 12 Jul, 2025 10 commits
-
-
Ying Sheng authored
-
Ying Sheng authored
-
Yineng Zhang authored
-
Yineng Zhang authored
-
Simo Lin authored
-
fzyzcjy authored
-
Xiaoyu Zhang authored
-
Yineng Zhang authored
-
fzyzcjy authored
Revert "[PD Disaggregation] replace transfer with batch transfer for better performance (#7236)" (#7968)
-
Yineng Zhang authored
-
- 11 Jul, 2025 5 commits
-
-
Qi Yuhang authored
-
Cheng Wan authored
-
Peng Zhang authored
-
ronnie_zheng authored
Co-authored-by:liupeng <liupeng374@huawei.com>
-
Atream authored
-
- 10 Jul, 2025 8 commits
-
-
Xiaoyu Zhang authored
-
ronnie_zheng authored
Co-authored-by:
ichernob <ichernobnn@gmail.com> Co-authored-by:
liupeng <liupeng374@huawei.com>
-
likesen-alibaba authored
-
Zaili Wang authored
-
Binyao Jiang authored
-
Mick authored
-
Simo Lin authored
-
kyleliang-nv authored
-
- 09 Jul, 2025 12 commits
-
-
Shuaiyi Zhang authored
-
almaslof authored
-
jianan-gu authored
-
Chunyuan WU authored
-
Cheng Wan authored
-
Xinyuan Tong authored
Signed-off-by:Xinyuan Tong <justinning0323@outlook.com>
-
Yineng Zhang authored
-
Yineng Zhang authored
-
Yikai Zhang authored
Co-authored-by:
Lifu Huang <lifu.hlf@gmail.com> Co-authored-by:
Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
-
Shangming Cai authored
Signed-off-by:Shangming Cai <caishangming@linux.alibaba.com>
-
Chunyuan WU authored
[CPU]convert topk_weights to fp32 for INT8 and FP8 paths (for llama4) and fix LmHead weight pack (#7818)
-
ybyang authored
-
- 08 Jul, 2025 5 commits
-
-
Brayden Zhong authored
-
Xinyuan Tong authored
Signed-off-by:Xinyuan Tong <justinning0323@outlook.com>
-
Xinyuan Tong authored
Signed-off-by:Xinyuan Tong <justinning0323@outlook.com>
-
Xinyuan Tong authored
Signed-off-by:Xinyuan Tong <justinning0323@outlook.com>
-
Xiaoyu Zhang authored
-