leavelet 7225a17c58 B300 NVFP4 port P1 stage-2: C2 flashinfer_cutedsl MoE runner + C3 flashinfer comm-fusion ...

Complete the flashinfer port ("port全"): ADD flashinfer_cutedsl.py (C2, deepep-paired NVFP4 MoE
runner; selectable via --moe-runner-backend flashinfer_cutedsl, already a MoeRunnerBackend enum) and
REPLACE flashinfer_comm_fusion.py to HEAD (C3, allreduce fusion). Both pull self-contained infra
modules target lacked: ADD model_executor/cuda_graph_config.py (cuda_graph_fully_disabled, 0 sglang
top-level imports) and runtime_context.py (get_parallel, lazy imports). comm_fusion consumers
(communicator.py is_flashinfer_allreduce_unavailable, layernorm.py flashinfer_allreduce_residual_rmsnorm)
verified present in HEAD.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-21 14:50:37 +00:00

..

sglang

B300 NVFP4 port P1 stage-2: C2 flashinfer_cutedsl MoE runner + C3 flashinfer comm-fusion

2026-06-21 14:50:37 +00:00

pyproject_cpu.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00

pyproject_npu.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00

pyproject_other.toml

chore: extract diffusion_common in python/pyproject_other.toml (#20803)

2026-03-19 10:39:16 +08:00

pyproject_xpu.toml

Upgrade transformers==5.3.0 (#17784)

2026-03-18 13:50:43 -07:00

pyproject.toml

new pyprojectoml

2026-06-10 05:54:43 +08:00