wangxiyuan 510bc9e1df [Misc] Cleanup useless current_platform import (#35715) ...

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

2026-03-02 09:36:54 +00:00

..

mla

[Feat] Add CUDA torch fallbacks for fp8_mqa_logits/fp8_paged_mqa_logits_torch function (#35271)

2026-02-28 10:12:00 +00:00

__init__.py

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

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

cpu_attn.py

[CPU][Perf] Accelerate Attention head for s390x using vector intrinsics (#34434)

2026-02-24 07:25:39 -08:00

fa_utils.py

[Misc] Cleanup useless current_platform import (#35715)

2026-03-02 09:36:54 +00:00

flash_attn_diffkv.py

[1/N][Attention] Restructure attention: move files (#31916)

2026-01-09 13:10:24 -08:00

flash_attn.py

[Attention] FA4 integration (#32974)

2026-03-01 23:44:57 +00:00

flashinfer.py

[Misc] Cleanup useless current_platform import (#35715)

2026-03-02 09:36:54 +00:00

flex_attention.py

[Bugfix][Attention] Explicitly report support for kv_cache_dtype bfloat16 (#32795)

2026-01-22 19:05:18 +00:00

gdn_attn.py

[GDN] Use CPU tensors to build GDN metadata (#34498)

2026-02-13 01:24:45 -08:00

linear_attn.py

[V1][Hybrid] Mamba Prefix Caching with align mode (#30877)

2026-01-23 09:56:48 -08:00

mamba1_attn.py

[Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798)

2026-03-01 20:40:23 +08:00

mamba2_attn.py

[Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798)

2026-03-01 20:40:23 +08:00

mamba_attn.py

[Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798)

2026-03-01 20:40:23 +08:00

registry.py

[Attention] Add FlashInfer Sparse MLA backend (#33451)

2026-02-12 17:21:54 +00:00

rocm_aiter_fa.py

[Platform] Add current_platform.num_compute_units interface (#35042)

2026-02-24 22:22:49 -08:00

rocm_aiter_unified_attn.py

[ROCm] Enabling encoder and encoder-decoder on ROCm and AITER unified backends (#35334)

2026-02-27 21:32:55 +00:00

rocm_attn.py

[ROCm] Add stablelm Head Size 80 To Supported Head Sizes For ROCM_ATTN (#35527)

2026-02-28 12:16:34 +08:00

short_conv_attn.py

[Misc] Add get_name to missing AttentionBackends (#32698)

2026-01-23 10:35:44 +00:00

tree_attn.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

triton_attn.py

[ROCm] AITER fused RoPE+KVCache (#33443)

2026-02-23 19:06:00 -08:00

utils.py

[perf] Avoid dtype promotion sync in mamba_get_block_table_tensor (#34870)

2026-02-20 06:21:56 -08:00