yinfengLiu f1e8fd27ae [ROCm] Add AITER FP8 ViT encoder attention (#49937) ...

Signed-off-by: Liuyinfeng01 <yinfeliu@amd.com>

2026-07-30 06:22:10 +00:00

..

__init__.py

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

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

chunked_prefill_paged_decode.py

[Bugfix] Don't read KV cache past seq_len in triton paged attn kernels (#47305)

2026-07-01 12:43:00 -07:00

common.py

[Attention][DSA] support dcp for FLASHINFER_MLA_SPARSE (#46076)

2026-07-01 00:32:20 -04:00

dcp_alltoall.py

[Bugfix][DCP] Cast LSE to fp32 in a2a combine to fix bf16 bitcast crash (#47801)

2026-07-08 11:41:26 -04:00

flashmla.py

Enable DeepSeek V4 and GLM-5.1 on SM120 (#43477)

2026-06-22 11:54:14 -07:00

int4_per_token_head.py

[Feature] Triton INT4 per-token-head KV cache quantization (#40835)

2026-06-24 10:21:25 +00:00

merge_attn_states.py

Fix FlashAttention MLA prefill V unpadding (#42642)

2026-07-08 15:22:20 +00:00

paged_attn.py

[XPU][9/N] clean up existing ipex code/doc (#34111)

2026-02-11 00:27:15 -08:00

prefix_prefill.py

[ROCm] [CI] Support cached K/V (key/value=None) in Triton prefix-prefill (#48257)

2026-07-29 23:31:51 -05:00

rocm_aiter_mla_sparse.py

[ROCm][Bugfix] Sanitize AITER paged-MQA logits before sparse top-k for DeepSeek-V4 (#49714)

2026-07-28 11:08:50 -07:00

triton_attention_helpers.py

Add Triton Backend for Unlimited-OCR R-SWA (#47102)

2026-07-03 00:11:50 -07:00

triton_decode_attention.py

[Bugfix] Fix int32 overflow in triton_decode_attention page offsets (#47671)

2026-07-06 10:36:15 -04:00

triton_fp8_mqa_logits.py

[ROCm][DSv4] Functional fixes for DeepSeek V4 on MI300X/MI325X (#45681)

2026-06-18 12:21:14 +00:00

triton_merge_attn_states.py

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089)

2026-07-29 14:10:58 +08:00

triton_prefill_attention.py

[ROCm] Fix pooling startup workspace lock (#47912)

2026-07-08 17:59:50 -05:00

triton_reshape_and_cache_flash.py

[2/N][KV-Cache Layout Refactor] Pack K/V into the content dim across attention backends (#44455)

2026-07-11 11:11:16 -04:00

triton_turboquant_decode.py

[Attention][TurboQuant] Share dequant buffers, eliminate float16_copy (#40941)

2026-04-27 13:48:36 +08:00

triton_turboquant_store.py

[2/N][KV-Cache Layout Refactor] Pack K/V into the content dim across attention backends (#44455)

2026-07-11 11:11:16 -04:00

triton_unified_attention_diffkv.py

[Model] Add DiffusionGemma Support (#45163)

2026-06-11 22:17:35 -07:00

triton_unified_attention.py

[Misc] Rename VLLM_TRITON_ATTN_USE_TD to VLLM_TRITON_USE_TD (#45781)

2026-07-14 10:32:57 +00:00

vit_attn_wrappers.py

[ROCm] Add AITER FP8 ViT encoder attention (#49937)

2026-07-30 06:22:10 +00:00

xpu_mla_sparse.py

[Bugfix] Prevent NaN poisoning in xpu_mla_sparse for fully-masked index chunks (#48366)

2026-07-27 09:06:07 +08:00