Mohammad Miadh Angkad 2bdd89a6cd [Kernel Slimming] Migrate NVFP4 kernels to JIT (#19437)

2026-03-05 15:22:28 +08:00

..

quantization

…

testing

…

__init__.py

[Kernel Slimming] Migrate NVFP4 kernels to JIT (#19437)

2026-03-05 15:22:28 +08:00

_fa4_interface.py

[NVIDIA] upstream FA4 (#15182)

2026-01-11 15:31:28 +08:00

allreduce.py

…

attention.py

…

cutlass_moe.py

…

elementwise.py

[Diffusion] Delete sgl-kernel outdated time_embedding kernel (#17278)

2026-01-28 14:18:53 +08:00

expert_specialization.py

…

flash_attn.py

[NVIDIA] upstream FA4 (#15182)

2026-01-11 15:31:28 +08:00

flash_mla.py

…

gemm.py

[Kernel Slimming] Migrate NVFP4 kernels to JIT (#19437)

2026-03-05 15:22:28 +08:00

grammar.py

…

kvcacheio.py

…

load_utils.py

fix(sgl-kernel): support CUDA 13 runtime preloading for DGX Spark (#18747)

2026-02-16 00:43:04 +08:00

mamba.py

[CPU] Optimize Qwen3-next model on CPU (#12525)

2026-01-29 22:03:58 -08:00

memory.py

…

moe.py

[Kernel Slimming] Migrate NVFP4 kernels to JIT (#19437)

2026-03-05 15:22:28 +08:00

sampling.py

use flashinfer.sampling (#18696)

2026-02-26 10:02:38 +08:00

scalar_type.py

…

sparse_flash_attn.py

…

spatial.py

…

speculative.py

…

test_utils.py

…

top_k.py

…

utils.py

…

version.py

chore: bump sgl-kernel version to 0.3.21 (#16888)

2026-01-14 13:27:49 +08:00