Hudson Xing 9d878c1f3e Optimize FP8 MLA KV cache writes with Triton kernel (#15522)

2025-12-25 12:35:39 -08:00

..

dequant_k_cache.py

[NSA] Fix NSA backend assertion error when running DeepSeek-V3.2 PP with radix-cache (#15086)

2025-12-14 17:13:18 -08:00

index_buf_accessor.py

[Performance] Optimize NSA Indexer K/S Buffer Access with Fused Triton Kernels (#13812)

2025-12-02 18:53:06 -08:00

nsa_backend_mtp_precompute.py

[Performance] optimize NSA backend metadata computation for multi-step speculative decoding (#14781)

2025-12-18 13:48:27 -08:00

nsa_indexer.py

[DSv32] Move deep_gemm.get_paged_mqa_logits_metadata to init time as metadata (#15040)

2025-12-19 13:23:33 -08:00

quant_k_cache.py

Optimize FP8 MLA KV cache writes with Triton kernel (#15522)

2025-12-25 12:35:39 -08:00

tilelang_kernel.py

…

transform_index.py

[DeepSeekV32] Bug fix to ensure page_table and result in same type (#12300)

2025-10-30 18:56:51 -07:00

triton_kernel.py

[DPSKv3.2] Rewrite nsa tilelang act_quant kernel to triton (#11450)

2025-10-10 23:13:46 -07:00

utils.py

[Performance] optimize NSA backend metadata computation for multi-step speculative decoding (#14781)

2025-12-18 13:48:27 -08:00