Xiaoyu Zhang 766d225fcc Add SGLang CUDA crash API logging inspired by FlashInfer (#20910)

2026-03-22 16:39:40 +08:00

..

quantization

…

testing

[kernel slimming] Clean many useless sgl-kernel deprecated kernels (#20277)

2026-03-14 16:45:54 +08:00

__init__.py

Add SGLang CUDA crash API logging inspired by FlashInfer (#20910)

2026-03-22 16:39:40 +08:00

_fa4_interface.py

…

allreduce.py

…

attention.py

…

cutlass_moe.py

…

debug_utils.py

Add SGLang CUDA crash API logging inspired by FlashInfer (#20910)

2026-03-22 16:39:40 +08:00

elementwise.py

[kernel slimming] Clean many useless sgl-kernel deprecated kernels (#20277)

2026-03-14 16:45:54 +08:00

expert_specialization.py

…

flash_attn.py

Add SGLang CUDA crash API logging inspired by FlashInfer (#20910)

2026-03-22 16:39:40 +08:00

flash_mla.py

…

gemm.py

[kernel slimming] Clean many useless sgl-kernel deprecated kernels (#20277)

2026-03-14 16:45:54 +08:00

grammar.py

…

kvcacheio.py

…

load_utils.py

Release sglang kernel 0.4.0 (#20440)

2026-03-16 20:34:58 +08:00

mamba.py

…

memory.py

[kernel slimming] Clean many useless sgl-kernel deprecated kernels (#20277)

2026-03-14 16:45:54 +08:00

moe.py

…

sampling.py

…

scalar_type.py

…

sparse_flash_attn.py

…

spatial.py

…

speculative.py

…

test_utils.py

…

top_k.py

…

utils.py

…

version.py

Release sglang kernel 0.4.0 (#20440)

2026-03-16 20:34:58 +08:00