Andreas Karatzas 9f0247cfa4

VLLM_USE_TRITON_FLASH_ATTN V0 variable deprecation (#27611) ...

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>

2025-11-11 18:34:36 -08:00

..

attention

[CPU] Refactor CPU attention backend (#27954)

2025-11-12 09:43:06 +08:00

core

[Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165)

2025-11-11 12:00:31 -05:00

mamba

[V1] [Hybrid] Mamba1 Automatic Prefix Caching (#26377)

2025-11-02 04:16:23 -08:00

moe

[Kernels] Split up fused_moe/layer.py, isolate more modular kernel code (#28064)

2025-11-11 07:29:02 -07:00

quantization

[Bugfix] Use latency MOE backend as default for Flashinfer and other misc fixes (#27439)

2025-11-07 04:18:39 -08:00

__init__.py

…

allclose_default.py

…

quant_utils.py

[Chore]:Extract math and argparse utilities to separate modules (#27188)

2025-10-26 04:03:32 -07:00

test_apply_repetition_penalties.py

…

test_fla_layernorm_guard.py

[PERF] [Qwen3-next] Speed up gated RMSNorm (#26207)

2025-10-12 08:27:50 +00:00

test_flex_attention.py

…

test_fused_quant_activation.py

…

test_onednn.py

[CPU] Refactor CPU attention backend (#27954)

2025-11-12 09:43:06 +08:00

test_shuffle_rows.py

…

test_top_k_per_row.py

[Deepseek v3.2] Remove extra logics in indexer (#26465)

2025-10-21 23:34:03 +00:00

utils.py

[V0 deprecation] Remove no longer used get_metadata_cls (#28370)

2025-11-10 14:32:09 +08:00