Johnsonms 34132d6da5 Kernel: optimize decoding metadata in NSA multi-spec backend with fused kernels (#17554)

2026-02-14 16:40:15 +08:00

..

diffusion

[Diffusion] Add diffusion time embedding to jit kernel (#17658)

2026-01-24 14:27:08 +08:00

elementwise

Kernel: optimize decoding metadata in NSA multi-spec backend with fused kernels (#17554)

2026-02-14 16:40:15 +08:00

gemm

[Kernel Slimming] Migrate GPTQ-Marlin repack kernel to JIT (#18543)

2026-02-13 22:29:22 +08:00

add_constant.cuh

[Refactor] Clean up JIT kernel utilites (#16884)

2026-01-13 17:54:16 +08:00

cuda_wait_value.cuh

[Refactor] Clean up JIT kernel utilites (#16884)

2026-01-13 17:54:16 +08:00

hicache.cuh

[Refactor] Clean up JIT kernel utilites (#16884)

2026-01-13 17:54:16 +08:00