sglang-botandsglang-bot c86ca12875 chore: bump sgl-kernel version to 0.3.21 (#16888) ...

Co-authored-by: sglang-bot <sglang-bot@users.noreply.github.com>

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

..

quantization

…

testing

…

__init__.py

[diffusion] kernel: timestep embedding kernel implementation (#12995)

2025-12-19 20:59:50 +08:00

_fa4_interface.py

[NVIDIA] upstream FA4 (#15182)

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

allreduce.py

[amd] Add deterministic all-reduce kernel for AMD (ROCm) (#15340)

2025-12-18 23:36:03 -08:00

attention.py

…

cutlass_moe.py

…

elementwise.py

[diffusion] kernel: timestep embedding kernel implementation (#12995)

2025-12-19 20:59:50 +08:00

expert_specialization.py

…

flash_attn.py

[NVIDIA] upstream FA4 (#15182)

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

flash_mla.py

…

fused_moe.py

…

gemm.py

…

grammar.py

…

hadamard.py

…

kvcacheio.py

…

load_utils.py

…

mamba.py

…

marlin.py

…

memory.py

…

moe.py

[sgl-kernel][1/2] Fused qk_norm_rope for GLM4.6 (#15141)

2025-12-18 17:07:04 +08:00

sampling.py

…

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