Cheng Wan 84c09913eb Moving _alloc_extend_naive out of npu allocator (#18200)

2026-02-04 02:09:55 -08:00

..

attention

[NPU] support dsv32 radixcache on ascend (#17964)

2026-02-03 03:34:12 +08:00

graph_runner

[NPU] Remove paged attention & Change fia to default attention (#17394)

2026-01-21 23:58:25 +08:00

modules

[NPU] enhance accuracy for model kimi-vl-a3b-instruct (#17480)

2026-01-30 15:19:42 +08:00

moe

[NPU] support the Enable return routed experts (#17025)

2026-02-01 18:31:39 +08:00

quantization

[NPU] NZ for non-quantized MOE, Qwen3 MOE double memory consumption fix (#15904)

2026-01-29 00:55:08 +08:00

allocator_npu.py

Moving _alloc_extend_naive out of npu allocator (#18200)

2026-02-04 02:09:55 -08:00

cmo.py

[NPU][1/N] NPU basic functions refactor and new modelslim quant type (#13359)

2025-12-04 16:15:31 +08:00

memory_pool_npu.py

[NPU] support dsv32 radixcache on ascend (#17964)

2026-02-03 03:34:12 +08:00

utils.py

[NPU] Adapt cann 8.5: use sfa and lightning indexer op from cann and CI update (#17615)

2026-01-27 19:03:53 +08:00