Chengji Yao e9d6a3db69

[TPU] make ptxla not imported when using tpu_commons (#23081) ...

Signed-off-by: Chengji Yao <chengjiyao@gmail.com>
Signed-off-by: Chengji Yao <chengjiyao@google.com>
Co-authored-by: Chengji Yao <chengjiyao@gmail.com>

2025-08-19 11:46:42 +08:00

..

mla

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

cpu_attn.py

[v1][attention] Support Hybrid Allocator + FlashInfer (#21412)

2025-07-30 01:45:29 +00:00

flash_attn.py

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

flashinfer.py

[Bugfix gpt-oss] Fix float32 convert for flashinfer sink support (#23016)

2025-08-16 11:16:00 -07:00

flex_attention.py

Support encoder_only attention for FlexAttention (#22273)

2025-08-06 18:37:14 -07:00

linear_attn.py

[V1] [Hybrid] Support Minimax-Text-01 in V1 (#22151)

2025-08-08 23:08:48 -07:00

mamba1_attn.py

[V1] - Split Prefill and Decode for Mamba1 models (#22653)

2025-08-15 08:59:52 +00:00

mamba2_attn.py

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

mamba_selectors.py

[Mamba] - refactor: Renamed mamba_attn to mamba2_attn (#22818)

2025-08-15 06:38:05 +00:00

pallas.py

[TPU] make ptxla not imported when using tpu_commons (#23081)

2025-08-19 11:46:42 +08:00

rocm_aiter_fa.py

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

tree_attn.py

[V1] Add tree drafting tests for eagle spec decoding (#22705)

2025-08-13 04:11:28 -07:00

triton_attn.py

[Core] Allow full cudagraph with separate attention routines and orthogonal to compilation, add support for FA2 and FlashInfer (#20059)

2025-08-15 10:01:39 -04:00

utils.py

[Kernel] Simplify get_kv_cache_layout and cache use_trtllm_attention env-dependent bit (#22735)

2025-08-16 00:14:08 +00:00

xformers.py

[V1] port xformers backend to v1 (#21342)

2025-08-05 10:04:46 -07:00