 Pranjal Shankhdharandpranjalssh
|
35df2fecde
|
[Fix] Stamp sequence-parallel state on dummy forward batches (#38564)
Co-authored-by: pranjalssh <pranjalssh@fb.com>
|
2026-09-09 01:03:03 -07:00 |
|
 Pranjal Shankhdharandpranjalssh
|
9c483cccfe
|
Support a same-size mixed q dtype in the fused RoPE kernels (#31834)
Co-authored-by: pranjalssh <pranjalssh@fb.com>
|
2026-07-24 16:19:08 -07:00 |
|
 Pranjal Shankhdharandpranjalssh
|
ad744c6c6b
|
[trtllm_mha] Fuse cuda-graph metadata rebuild into one triton kernel (#29843)
Co-authored-by: pranjalssh <pranjalssh@fb.com>
|
2026-07-03 22:24:28 -07:00 |
|