TensorRT-LLMs/cpp/kernels/fmha_v2/src/fmha
Zhou Yuxin f01101f687
[None][feat] Hopper Fp8 context mla (#7116)
Signed-off-by: Yuxin <yuxinz@nvidia.com>
2025-08-26 17:10:20 +08:00
..
hopper [None][feat] Hopper Fp8 context mla (#7116) 2025-08-26 17:10:20 +08:00
warpspec [None][feat] Hopper Fp8 context mla (#7116) 2025-08-26 17:10:20 +08:00
alibi_params.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
fragment.h [None][feat] Add support for Hopper MLA chunked prefill (#6655) 2025-08-14 10:39:26 +08:00
gemm.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
gmem_tile_o_packed.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
gmem_tile_o.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
gmem_tile_ps.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
gmem_tile_qkv_packed.h [None][feat] Use Separate QKV Input Layout for Context MLA (#6538) 2025-08-19 22:04:48 +08:00
gmem_tile_qkv.h hopper-style context MLA (#5713) 2025-07-23 14:37:20 +08:00
kernel_traits.h [None][feat] Use Separate QKV Input Layout for Context MLA (#6538) 2025-08-19 22:04:48 +08:00
mask.h [TRTLLM-6674][feat] (Breaking Change) Hopper SWA non-cyclic kernels + KV reuse + Spec Dec (#6379) 2025-08-05 07:47:41 +00:00
numeric_types.h fix fmha v2 tests (#4661) 2025-05-27 09:47:01 +08:00
paged_kv_cache.h chore: Improve documentation of Kv_block_array (#5765) 2025-07-05 22:25:27 +02:00
smem_tile_o.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
smem_tile_qkv.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
smem_tile_v.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
smem_tile.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
softmax.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
traits.h infra: open source fmha v2 kernels (#4185) 2025-05-15 10:56:34 +08:00
utils.h Clean: fmha codes (#4496) 2025-05-21 11:45:47 +08:00