- 15 Jan, 2026 26 commits
-
-
Pleaplusone authored
Signed-off-by:ganyi <ygan@amd.com>
-
Pleaplusone authored
[ROCm][Perf] Enable shuffle kv cache layout and assembly paged attention kernel for `AiterFlashAttentionBackend` (#29887) Signed-off-by:ganyi <ygan@amd.com>
-
Dipika Sikka authored
Signed-off-by:
Dipika Sikka <dipikasikka1@gmail.com> Co-authored-by:
Michael Goin <mgoin64@gmail.com>
-
Matthew Bonanni authored
[Attention][MLA] Make `FLASHINFER_MLA` the default MLA backend on Blackwell, and TRTLLM the default prefill (#32339) Signed-off-by:
Matthew Bonanni <mbonanni@redhat.com> Co-authored-by:
Wentao Ye <44945378+yewentao256@users.noreply.github.com>
-
brian033 authored
Signed-off-by:
brian033 <85883730+brian033@users.noreply.github.com> Co-authored-by:
TJian <tunjian.tan@embeddedllm.com>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
rasmith authored
Signed-off-by:
Randall Smith <ransmith@amd.com> Co-authored-by:
Randall Smith <ransmith@amd.com>
-
Douglas Lehr authored
Signed-off-by:
Doug Lehr <douglehr@amd.com> Co-authored-by:
Doug Lehr <douglehr@amd.com>
-
Chauncey authored
Signed-off-by:chaunceyjiang <chaunceyjiang@gmail.com>
-
rongfu.leng authored
Signed-off-by:lengrongfu <lenronfu@gmail.com>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
seeksky authored
Signed-off-by:seekskyworld <djh1813553759@gmail.com>
-
dtc authored
Signed-off-by:Tianchen Ding <dtcccc@linux.alibaba.com>
-
Chauncey authored
Signed-off-by:chaunceyjiang <chaunceyjiang@gmail.com>
-
Andreas Karatzas authored
Signed-off-by:Andreas Karatzas <akaratza@amd.com>
-
Ofir Zafrir authored
Signed-off-by:Ofir Zafrir <ofir.zafrir@intel.com>
-
Lucas Wilkinson authored
Signed-off-by:
Lucas Wilkinson <lwilkins@redhat.com> Co-authored-by:
Eldar Kurtić <8884008+eldarkurtic@users.noreply.github.com>
-
Ning Xie authored
Signed-off-by:Andy Xie <andy.xning@gmail.com>
-
rasmith authored
[CI][AMD][Quantization][BugFix] Fix fp8 max in quant_utils.py and update test_fp8_quant.::test_static_fp8_quant_group_2d to use correct fp8 dtype and adjust atol/rtol (#32201) Signed-off-by:Randall Smith <ransmith@amd.com>
-
Micah Williamson authored
[ROCm][CI] Disable async scheduling on ROCm for test_structured_output[meta-llama/Meta-Llama-3.1-8B-Instruct-xgrammar-auto-speculative_config9] (#32355) Signed-off-by:Micah Williamson <micah.williamson@amd.com>
-
kzwrime authored
Signed-off-by:kunzh <zhikun.wu@outlook.com>
-
Li Wang authored
Signed-off-by:wangli <wangli858794774@gmail.com>
-
Shiyan Deng authored
Signed-off-by:Shiyan Deng <dsy842974287@meta.com>
-
baonudesifeizhai authored
Signed-off-by:baonudesifeizhai <baonudesifeizhai@gmail.com>
-
Ryan Rock authored
Signed-off-by:Ryan Rock <ryan.rock@amd.com>
-
- 14 Jan, 2026 14 commits
-
-
dolpm authored
Signed-off-by:dolpm <34420038+dolpm@users.noreply.github.com>
-
Lumosis authored
Signed-off-by:Lihao Ran <imlihao.ran@gmail.com>
-
vllmellm authored
[Bugfix][ROCm][performance] Resolve the performance regression issue of the Qwen3-Next-80B-A3B-Thinking under rocm_atten (#32336) Signed-off-by:vllmellm <vllm.ellm@embeddedllm.com>
-
Aleksandr Samarin authored
Signed-off-by:
Aleksandr Samarin <astrlrd@nebius.com> Signed-off-by:
southfreebird <yvorott@gmail.com> Co-authored-by:
southfreebird <yvorott@gmail.com>
-
qli88 authored
Signed-off-by:Qiang Li <qiang.li2@amd.com>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
Ning Xie authored
Signed-off-by:Andy Xie <andy.xning@gmail.com>
-
Chauncey authored
Signed-off-by:chaunceyjiang <chaunceyjiang@gmail.com>
-
Shanshan Shen authored
Signed-off-by:shen-shanshan <467638484@qq.com>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
Chauncey authored
Signed-off-by:chaunceyjiang <chaunceyjiang@gmail.com>
-
Cyrus Leung authored
Signed-off-by:DarkLight1337 <tlleungac@connect.ust.hk>
-
Roger Wang authored
Signed-off-by:Roger Wang <hey@rogerw.io>
-
sangho.lee authored
Signed-off-by:
sanghol <sanghol@allenai.org> Signed-off-by:
Isotr0py <mozf@mail2.sysu.edu.cn> Co-authored-by:
Isotr0py <mozf@mail2.sysu.edu.cn>
-