fzyzcjy 5c66c4424f Support new DeepGEMM format in per token group quant (#7146)

2025-06-13 02:00:22 -07:00

..

__init__.py

[sgl-kernel] Add cuda kernel for moe_ep_silu_and_mul (#6919)

2025-06-11 20:43:08 -07:00

allreduce.py

support 1 shot allreduce in 1-node and 2-node using mscclpp (#6277)

2025-06-04 22:11:24 -07:00

attention.py

Remove 200us slow concat kernel (part 1: kernel) (#7145)

2025-06-13 01:58:29 -07:00

elementwise.py

[Feat] Enable PDL automatically on Hopper architecture (#5981)

2025-06-01 12:30:17 -07:00

flash_attn.py

Revert "fix some typos" (#6244)

2025-05-12 12:53:26 -07:00

gemm.py

Support new DeepGEMM format in per token group quant (#7146)

2025-06-13 02:00:22 -07:00

grammar.py

fix sgl-kernel unit tests (#5666)

2025-04-23 01:18:30 -07:00

moe.py

[sgl-kernel] Add cuda kernel for moe_ep_silu_and_mul (#6919)

2025-06-11 20:43:08 -07:00

sampling.py

Fix sampler nan check when calling top_k_top_p_sampling_from_probs (#5546)

2025-04-19 21:47:23 -07:00

sparse_flash_attn.py

[Feat] QWen-1M context support[1/2]: Update block sparse attention backend utils kernel (#5847)

2025-04-28 11:03:17 -07:00

speculative.py

use default for torch.ops (#4835)

2025-03-27 19:09:58 -07:00

utils.py

misc: cache is_hopper_arch (#6799)

2025-06-01 15:28:31 -07:00

version.py

feat: update blackwell setup (#7119)

2025-06-12 01:54:40 -07:00