Benjamin Chislett d6b3d39b6d

[Cleanup] Refactor FlashInferMetadataBuilder (#29128) ...

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>

2025-12-18 14:45:30 -08:00

..

mla

[ROCm][MTP] Support MTP for AITER MLA backend (#28624)

2025-12-16 14:10:26 +00:00

__init__.py

…

cpu_attn.py

[CPU] Support for Whisper (#30062)

2025-12-10 04:58:42 -08:00

flash_attn.py

[Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627)

2025-12-16 17:10:16 -05:00

flashinfer.py

[Cleanup] Refactor FlashInferMetadataBuilder (#29128)

2025-12-18 14:45:30 -08:00

flex_attention.py

[Fix][FlexAttention] return max logical block index to handle reused blocks (#30915)

2025-12-18 06:42:21 +00:00

gdn_attn.py

[main][BugFix] Fixed an accuracy bug of Qwen3-next-MTP when batched inferring (#30632)

2025-12-14 01:32:16 -08:00

linear_attn.py

[Attention] add _cudagraph_support for linear attention (#28934)

2025-11-25 12:25:20 +08:00

mamba1_attn.py

[Attention][CUDAGraph] Remove CG padding from attention backends (#29352)

2025-12-02 13:48:08 -05:00

mamba2_attn.py

[Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627)

2025-12-16 17:10:16 -05:00

mamba_attn.py

[Core] Refactor padding logic and pad for CUDA graphs before attention metadata building (#28579)

2025-11-26 14:07:13 -05:00

pallas.py

…

rocm_aiter_fa.py

[ROCm][Attention] Sliding window support for AiterFlashAttentionBackend (#29234)

2025-11-30 11:31:50 +00:00

rocm_aiter_unified_attn.py

[ROCm] Support for Whisper v1 with Aiter Unified Attention and Aiter Flash Attention (#28376)

2025-11-24 03:26:00 +00:00

rocm_attn.py

[ROCm][CI] Reduce Flakiness For test_async_scheduling Using ROCM_ATTN With FP32 (#30811)

2025-12-18 10:27:37 +08:00

short_conv_attn.py

[Attention][CUDAGraph] Remove CG padding from attention backends (#29352)

2025-12-02 13:48:08 -05:00

tree_attn.py

…

triton_attn.py

[v1] Add PrefixLM support to TritonAttention backend (#30386)

2025-12-17 16:05:24 -08:00

utils.py

[Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627)

2025-12-16 17:10:16 -05:00