Michael Goin 61445453df [UX] Rename CUTLASS_MLA_VLLM_V1 to CUTLASS_MLA (#21966) ...

Signed-off-by: mgoin <mgoin64@gmail.com>

2025-07-30 20:40:34 -07:00

..

mla

[UX] Rename CUTLASS_MLA_VLLM_V1 to CUTLASS_MLA (#21966)

2025-07-30 20:40:34 -07:00

__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

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

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

flashinfer.py

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

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

flex_attention.py

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

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

mamba_attn.py

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

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

mamba_selectors.py

[v1][mamba] Added mamba_type into MambaSpec (#21715)

2025-07-28 08:15:55 +00:00

pallas.py

[Attention] Clean up iRoPE in V1 (#21188)

2025-07-21 09:10:30 -07:00

rocm_aiter_fa.py

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

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

triton_attn.py

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

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

utils.py

Override attention metadata for fast prefill in some KV sharing setups (#21590)

2025-07-30 08:54:15 -07:00