Fix MXFP8 MoE weight sizing for non-gated models

f57f24b

Select commit

Loading

Failed to load commit list.

Uh oh!

There was an error while loading. Please reload this page.

Sign in for the full log view

PR States on: pull_request_target

update-pr-body

Auto Label PRs on: pull_request_target 1

label

Lint on: pull_request 2

lint

PR Test (sgl-router) on: pull_request 2

gate

tier-1 — lint

tier-2 — build + test

tier-3 — docker (placeholder)

tier-3 — k8s integration

tier-3 — e2e

finish

PR Test (MUSA) on: pull_request

check-changes

pr-gate / pr-gate

multimodal-gen-test-1-gpu-musa

multimodal-gen-test-2-gpu-musa

multimodal-gen-layer-unit-test-musa

sgl-kernel-unit-test-musa

pr-test-musa-finish

PR Test Extra (AMD) on: pull_request 2

call-gate / pr-gate

extra-a-test-1-gpu-small-amd${{ ((inputs.rocm_version && (inputs.rocm_version != 'rocm724') && format('-{0}', inputs.rocm_version)) || '') }} (linux-${{ (inputs.runner_arch || 'mi300') }}-1gpu-sglang)

extra-a-test-1-gpu-large-amd${{ ((inputs.rocm_version && (inputs.rocm_version != 'rocm724') && format('-{0}', inputs.rocm_version)) || '') }} (linux-${{ (inputs.runner_arch || 'mi300') }}-1gpu-sglang)

extra-a-test-2-gpu-large-amd${{ ((inputs.rocm_version && (inputs.rocm_version != 'rocm724') && format('-{0}', inputs.rocm_version)) || '') }} (linux-${{ (inputs.runner_arch || 'mi300') }}-2gpu-sglang)

pr-test-amd-extra-finish

PR Test Extra on: pull_request 2

check-changes / check-changes

call-gate / pr-gate

sgl-kernel-build-wheels

rust-ext-build

extra-a-test-1-gpu-small

extra-a-test-1-gpu-large

extra-a-test-2-gpu-large

extra-b-test-4-gpu-h100

extra-b-test-4-gpu-b200

extra-b-test-8-gpu-h200

pr-test-extra-finish

notify-pr-states

PR Test (NPU) on: pull_request 3

check-changes

set-image-config

pr-gate / pr-gate

base-a-test-1-npu-a2 / run (0)

base-b-test-1-npu-a3 / run (0)

base-b-test-2-npu-a3 / run (0)

base-b-test-4-npu-a3 / run (0)

base-b-test-4-npu-a3 / run (1)

base-b-test-8-npu-a3 / run (0)

base-b-test-16-npu-a3 / run (0)

multimodal-gen-test-1-npu-a3 (0)

multimodal-gen-test-1-npu-a3 (1)

multimodal-gen-test-2-npu-a3 (0)

multimodal-gen-test-2-npu-a3 (1)

base-c-test-acc-2-npu-a3 / base-c-test-acc-2-npu-a3

base-c-test-acc-4-npu-a3 / base-c-test-acc-4-npu-a3

base-c-test-acc-8-npu-a3 / base-c-test-acc-8-npu-a3

base-c-test-acc-16-npu-a3 / base-c-test-acc-16-npu-a3

PR Test (XPU) on: pull_request

check-changes

pr-gate / pr-gate

stage-a-test-1-gpu-xpu

PR Test (Xeon) on: pull_request

check-changes

pr-gate / pr-gate

build-test (xeon-gnr, base-b-test-cpu)

PR Test (MLX) on: pull_request 1

check-changes

pr-gate / pr-gate

stage-a-unit-test-mlx

stage-b-e2e-test-mlx

pr-test-mlx-finish

PR Test (Arm64) on: pull_request 2

check-changes

pr-gate / pr-gate

build-test

PR Test ROCm 7.2 (AMD) on: pull_request 1

call-gate / pr-gate

call-pr-test-amd-extra-rocm720

check-changes

sgl-kernel-unit-test-amd-rocm720 (linux-${{ (inputs.runner_arch || 'mi300') }}-1gpu-sglang)

sgl-kernel-unit-test-2-gpu-amd-rocm720 (linux-${{ (inputs.runner_arch || 'mi300') }}-2gpu-sglang)

stage-a-test-1-gpu-small-amd-rocm720 (linux-mi300-1gpu-sglang)

jit-kernel-unit-test-amd-rocm720 (linux-${{ (inputs.runner_arch || 'mi300') }}-1gpu-sglang)

jit-kernel-benchmark-test-amd-rocm720 (linux-${{ (inputs.runner_arch || 'mi300') }}-1gpu-sglang)

wait-for-stage-a-amd-rocm720

multimodal-gen-test-1-gpu-amd-rocm720 (linux-${{ (inputs.runner_arch || 'mi300') }}-1gpu-sglang, ${{ matrix.part }})

multimodal-gen-test-2-gpu-amd-rocm720 (linux-${{ (inputs.runner_arch || 'mi300') }}-2gpu-sglang, ${{ matrix.part }})

PR Test Base on: pull_request 33

check-changes / check-changes

call-pr-test-extra

call-gate / pr-gate

wait-for-base-a

sgl-kernel-build-wheels

sgl-kernel-build-wheels-arm

rust-ext-build / Restore Rust Ext

rust-ext-build / Build Rust Ext

wait-for-base-b

call-sgl-kernel-tests

call-jit-kernel-tests

base-a-test-1-gpu-small / base-a-test-1-gpu-small (0)

base-a-test-cpu / base-a-test-cpu (0)

base-a-test-cpu / base-a-test-cpu (1)

base-a-test-cpu / base-a-test-cpu (2)

base-a-test-cpu / base-a-test-cpu (3)

base-a-test-cpu / base-a-test-cpu (4)

base-a-test-cpu / base-a-test-cpu (5)

base-a-test-cpu / base-a-test-cpu (6)

base-a-test-cpu / base-a-test-cpu (7)

base-a-test-cpu / base-a-test-cpu (8)

base-a-test-cpu / base-a-test-cpu (9)

base-a-test-cpu / base-a-test-cpu (10)

base-a-test-cpu / base-a-test-cpu (11)

base-b-test-1-gpu-small / base-b-test-1-gpu-small (0)

base-b-test-1-gpu-small / base-b-test-1-gpu-small (1)

base-b-test-1-gpu-small / base-b-test-1-gpu-small (2)

base-b-test-1-gpu-small / base-b-test-1-gpu-small (3)

base-b-test-1-gpu-small / base-b-test-1-gpu-small (4)

base-b-test-1-gpu-small / base-b-test-1-gpu-small (5)

base-b-test-1-gpu-small / base-b-test-1-gpu-small (6)

base-b-test-1-gpu-small / base-b-test-1-gpu-small (7)

base-b-test-1-gpu-large / base-b-test-1-gpu-large (0)

base-b-test-1-gpu-large / base-b-test-1-gpu-large (1)

base-b-test-1-gpu-large / base-b-test-1-gpu-large (2)

base-b-test-1-gpu-large / base-b-test-1-gpu-large (3)

base-b-test-1-gpu-large / base-b-test-1-gpu-large (4)

base-b-test-1-gpu-large / base-b-test-1-gpu-large (5)

base-b-test-1-gpu-large / base-b-test-1-gpu-large (6)

base-b-test-1-gpu-large / base-b-test-1-gpu-large (7)

base-b-test-2-gpu-large / base-b-test-2-gpu-large (0)

base-b-test-2-gpu-large / base-b-test-2-gpu-large (1)

base-b-test-2-gpu-large / base-b-test-2-gpu-large (2)

base-b-test-2-gpu-large / base-b-test-2-gpu-large (3)

base-b-test-2-gpu-large / base-b-test-2-gpu-large (4)

base-b-test-4-gpu-b200 / base-b-test-4-gpu-b200 (0)

call-multimodal-gen-tests

update-pr-body

succeeded Aug 23, 2026 in 6s

Loading

Re-running jobs...