TensorRT-LLMs/cpp/kernels
DylanChen-NV b275635a9a
[https://nvbugs/5498478][fix] Fix eagle3 fp8 kv target model + bf16 draft model + chunked prefill (#8910)
Signed-off-by: Dylan Chen <191843203+DylanChen-NV@users.noreply.github.com>
2025-11-06 07:41:21 -08:00
..
fmha_v2 [https://nvbugs/5498478][fix] Fix eagle3 fp8 kv target model + bf16 draft model + chunked prefill (#8910) 2025-11-06 07:41:21 -08:00
xqa [None][feat] Fix attention sink load in xqa (#8836) 2025-11-03 09:39:45 +08:00