Chen Zhang a89209b78d [v1] Support mamba2 (#19327) ...

Signed-off-by: Chen Zhang <zhangch99@outlook.com>

2025-06-18 20:34:15 +00:00

..

mla

[CUDA] Enable full cudagraph for FlashMLA (#18581)

2025-06-13 18:12:26 +00:00

__init__.py

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

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

cpu_attn.py

[CUDA] Enable full cudagraph for FlashMLA (#18581)

2025-06-13 18:12:26 +00:00

flash_attn.py

[Feature][ROCm] Add full graph capture support for TritonAttentionBackend (#19158)

2025-06-17 17:03:06 -04:00

flashinfer.py

[V1][Kernel] Flashinfer HND KV cache layout (#19280)

2025-06-17 09:09:22 -04:00

flex_attention.py

Fixes IMA for TP w/ flex-attention (#19712)

2025-06-17 04:01:50 +00:00

mamba_attn.py

[v1] Support mamba2 (#19327)

2025-06-18 20:34:15 +00:00

pallas.py

[TPU] support attention head dim smaller than 128 (#19620)

2025-06-16 06:40:53 +00:00

rocm_aiter_fa.py

[Hardware][AMD] integrate aiter chunked prefill into vllm (#18596)

2025-06-18 08:46:51 -07:00

triton_attn.py

[Feature][ROCm] Add full graph capture support for TritonAttentionBackend (#19158)

2025-06-17 17:03:06 -04:00

utils.py

[Feature][ROCm] Add full graph capture support for TritonAttentionBackend (#19158)

2025-06-17 17:03:06 -04:00