7 Commits
Author SHA1 Message Date
Bo Li cdd4638b17 [Feature][Diffusion] Expose detailed pipeline timings (#6822)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2026-09-09 09:58:42 +00:00
Bo Li fda3af8bbc [Bugfix] Preserve BF16 residual semantics in fused MiniMax-H3 modulation (#6878)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2026-09-04 02:01:34 +08:00
Bo Li 5d20f6b900 [Doc] Refine TRTLLM attention guidance (#6724)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2026-09-02 19:42:37 +08:00
Bo Li 6f16f9546d [Bugfix][Kernel] Stage strided Ulysses QKV with copy engine (#6814)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2026-08-31 17:28:49 +08:00
Bo Li 51b7565f33 [perf] Add mask-free TRTLLM packed-padding path (#6542)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
2026-08-25 07:45:21 +00:00
596c16a550 [Kernel] Fuse Q/K RMSNorm and RoPE (#5990)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Signed-off-by: Mengjie Zhao <zmj0129@gmail.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-14 00:46:59 +00:00
d219d93bbb [Attention] Refine TRTLLM attention support for MiniMax H3 (#5779)
Signed-off-by: Bo Li <22713281+bobboli@users.noreply.github.com>
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Signed-off-by: lishunyang12 <lishunyang12@163.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: lishunyang12 <lishunyang12@163.com>
2026-08-06 09:38:17 +00:00