AIbin a7392a0ff9 【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886) ...

* support MLA chunk_size auto search & cuda_graph

2025-09-11 10:46:09 +08:00

..

attention_updater.cuh

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

batch_mla_with_paged_kv_cache.cu

【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886)

2025-09-11 10:46:09 +08:00

batch_mla_with_paged_kv_cache.h

【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886)

2025-09-11 10:46:09 +08:00

epilogue.cuh

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

kernel_traits.cuh

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

mainloop_load.cuh

【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886)

2025-09-11 10:46:09 +08:00

mainloop_mma.cuh

【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886)

2025-09-11 10:46:09 +08:00

mla_hopper.cuh

【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886)

2025-09-11 10:46:09 +08:00

named_barrier.cuh

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

utils.cuh

【Inference Optimize】DeepSeek-V3-model MLA Optimize (#3886)

2025-09-11 10:46:09 +08:00