Zijie Tian 82ed34fc2d [opt] optimize nanovllm performance compareable with vllm.

2025-12-25 03:47:07 +08:00

..

sgdma_cpp

[WIP] Added sgDMA operator for scatter kvcache communication.

2025-12-24 23:48:52 +08:00

__init__.py

[WIP] NEED refactor nanovllm mechenism.

2025-12-22 23:52:56 +08:00

test_attention_offload.py

[opt] optimize nanovllm performance compareable with vllm.

2025-12-25 03:47:07 +08:00

test_chunked_attention.py

[WIP] remove num_prefetch_blocks varible.

2025-12-24 18:22:26 +08:00

test_offload_engine.py

[WIP] NEED refactor nanovllm mechenism.

2025-12-22 23:52:56 +08:00

test_pinned_memory_slice.py

[WIP] NEED to modify communication.

2025-12-24 21:57:51 +08:00

test_pinned_transfer.py

[WIP] NEED to modify communication.

2025-12-24 21:57:51 +08:00

test_prefill.py

[WIP] remove num_prefetch_blocks varible.

2025-12-24 18:22:26 +08:00

test_sgdma.py

[WIP] replace merge attention with triton kernel.

2025-12-25 01:07:05 +08:00

test_sim.py

[WIP] remove num_prefetch_blocks varible.

2025-12-24 18:22:26 +08:00