TensorRT-LLMs/tests/unittest/_torch/attention/sparse
2025-11-05 07:57:09 -08:00
..
test_dsa_indexer.py [TRTLLM-8976][feat] Move indexer-k-cache to KVCacheManager (#8699) 2025-10-29 08:04:26 -07:00
test_flash_mla.py [TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405) 2025-10-24 13:40:41 -04:00
test_rocketkv.py [TRTLLM-8536][feat] Add the sparse attention framework and one use case--RocketKV support (#8086) 2025-10-14 08:23:16 -07:00
test_sparse_mla_forward.py [TRTLLM-8768][chore] Fuse QK down_proj with indexer K + weight_proj for FP4 ckpt (#8771) 2025-11-05 07:57:09 -08:00