Wallas HenriqueandMichael Goin c27df94e1f [Bugfix] Fix chunked prefill with model dtype float32 on Turing Devices (#9850) ...

Signed-off-by: Wallas Santos <wallashss@ibm.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>

2024-11-25 12:23:32 -05:00

..

blocksparse_attention

[Kernel] Explicitly specify other value in tl.load calls (#9014)

2024-11-18 11:39:40 -08:00

__init__.py

[Core] Refactor Attention Take 2 (#3462)

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

hpu_paged_attn.py

[Hardware][Intel-Gaudi] Add Intel Gaudi (HPU) inference backend (#6143)

2024-11-06 01:09:10 -08:00

ipex_attn.py

[Hardware][CPU] Support chunked-prefill and prefix-caching on CPU (#10355)

2024-11-20 10:57:39 +00:00

paged_attn.py

Support Roberta embedding models (#9387)

2024-11-14 21:23:29 +00:00

prefix_prefill.py

[Bugfix] Fix chunked prefill with model dtype float32 on Turing Devices (#9850)

2024-11-25 12:23:32 -05:00

triton_flash_attention.py

[ROCm][AMD][Bugfix] adding a missing triton autotune config (#4845)

2024-05-16 10:46:52 -07:00