4 people f8460ef236 [Kernel][DSv4.1] Bump FlashMLA to the 2026.09.30 release and its interleaved V4.1 KV cache (#61371) ...

Signed-off-by: juntianl <juntianl@inferact.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: Kimi Code <noreply@moonshot.ai>
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai>

2026-10-15 13:58:25 -07:00

..

test_activation.py

[CI][ROCm] Deprecate DinD for MI250 test groups (#56162)

2026-09-18 14:13:35 -07:00

test_conv.py

[Kimi-K3][Perf] Dispatch GEMM for vision patch embedder (#58527)

2026-09-24 18:30:11 -07:00

test_fused_shared_expert.py

[Chore] Use upstream Transformers DeepseekV4Config (#61392)

2026-10-15 01:08:08 -07:00

test_mla_short_prefill_indexer.py

[Kernel][DSv4.1] Bump FlashMLA to the 2026.09.30 release and its interleaved V4.1 KV cache (#61371)

2026-10-15 13:58:25 -07:00

test_mm_input_norm.py

[MM] Keep device input normalization fused when encoder compilation is enabled (#59195)

2026-09-30 11:08:24 +00:00

test_pooler_activations.py

Disable mypy arg-type and assignment checks in tests (#59428)

2026-09-30 15:18:50 +00:00

test_pooler_heads.py

[Feature][Pooling] Add offline fixed-length late chunking (#60164)

2026-10-13 11:16:21 +00:00

test_pooler_methods.py

[Feature][Pooling] Add offline fixed-length late chunking (#60164)

2026-10-13 11:16:21 +00:00

test_rocm_unquantized_gemm.py

[ROCm][Perf] Pad fp16/bf16 GEMM weight row stride for L2 cache (#55090)

2026-10-15 14:26:32 +00:00