Yineng Zhang 6e7239f912 release 0.0.4.post3 sgl-kernel (#4331)

2025-03-12 01:05:16 -07:00

..

__init__.py

Add awq dequantize kernel to sgl with 1x to 3x speedup (#4104)

2025-03-12 00:10:02 -07:00

allreduce.py

…

attention.py

…

elementwise.py

Optimize rope in sgl kernel (#4267)

2025-03-10 10:07:45 -07:00

gemm.py

fix awq_dequantize (#4333)

2025-03-12 01:04:38 -07:00

moe.py

…

sampling.py

…

speculative.py

…

utils.py

…

version.py

release 0.0.4.post3 sgl-kernel (#4331)

2025-03-12 01:05:16 -07:00