4 people fb4c7f8ef0 [Kernel] [V1] Further optimizations to ROCm (Triton) Backend to better handle GQA. (#14431) ...

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Jan van Lunteren <jvl@zurich.ibm.com>
Co-authored-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Co-authored-by: Chih-Chieh Yang <chih.chieh.yang@ibm.com>

2025-03-13 20:42:27 -07:00

..

blocksparse_attention

[Misc] Add SPDX-License-Identifier headers to python source files (#12628)

2025-02-02 11:58:18 -08:00

__init__.py

[Core] Refactor Attention Take 2 (#3462)

2024-03-25 04:39:33 +00:00

chunked_prefill_paged_decode.py

[Kernel] [V1] Further optimizations to ROCm (Triton) Backend to better handle GQA. (#14431)

2025-03-13 20:42:27 -07:00

flashmla.py

[Kernel] FlashMLA integration (#13747)

2025-02-27 10:35:08 +08:00

hpu_paged_attn.py

[Hardware][Gaudi][Feature] Support Contiguous Cache Fetch (#12139)

2025-02-18 19:40:19 -08:00

ipex_attn.py

[CPU] Upgrade CPU backend to torch-2.6 (#13381)

2025-03-12 10:41:13 +00:00

nki_flash_attn.py

[neuron] add reshape_and_cache (#14391)

2025-03-10 18:37:29 -07:00

paged_attn.py

[V1][Kernel] Refactor the prefix_prefill kernel so that the caller no longer has to pass in the context lengths (#13095)

2025-02-22 05:25:41 -08:00

prefix_prefill.py

[Kernel] [V1] Improved performance for V1 Triton (ROCm) backend (#14152)

2025-03-06 07:39:16 -08:00

triton_decode_attention.py

[core] Perf improvement for DSv3 on AMD GPUs (#13718)

2025-02-27 22:14:30 +00:00

triton_flash_attention.py

[Misc] Fix improper placement of SPDX header in scripts (#12694)

2025-02-03 11:16:59 -08:00

triton_merge_attn_states.py

[Attention] MLA with chunked prefill (#12639)

2025-02-21 15:30:12 -08:00