Auto Label PRs · Workflow runs · sgl-project/sglang · GitHub

Actions

All workflows
Workflows
- Build and Push Development Docker Images Build and Push Development Docker Images
- Cancel All Pending PR Test Runs Cancel All Pending PR Test Runs
- CI Monitor CI Monitor
- Nightly Test (Nvidia) Nightly Test (Nvidia)
- PR Test PR Test
- .github/workflows/pr-gate.yml .github/workflows/pr-gate.yml
- Auto Format Code Auto Format Code
- Auto Label PRs Auto Label PRs
- Bot Bump Kernel Version Bot Bump Kernel Version
- Bot Bump Kernel Version to SGLang Bot Bump Kernel Version to SGLang
Management
- Caches
- Deployments

Auto Label PRs

Actions

Loading...
Loading

5,574 workflow runs

5,574 workflow runs

[Models] Add NVIDIA Eagle 2.5 VLM Auto Label PRs #5575: Pull request #13166 synchronize by Jonahcb

9s

9s

[Diffusion] add rocm support Auto Label PRs #5574: Pull request #13760 synchronize by zyzshishui

8s

8s

[Diffusion] add rocm support Auto Label PRs #5573: Pull request #13760 synchronize by zyzshishui

9s

9s

[Diffusion] add rocm support Auto Label PRs #5572: Pull request #13760 synchronize by zyzshishui

7s

7s

Fix LMCache unit test and init bug Auto Label PRs #5571: Pull request #14005 synchronize by DongDongJu

9s

9s

[Diffusion] add rocm support Auto Label PRs #5570: Pull request #13760 synchronize by zyzshishui

10s

10s

fix: Remove OOM models from AMD nightly test Auto Label PRs #5569: Pull request #14068 synchronize by sunxxuns

8s

8s

fix: Remove OOM models from AMD nightly test Auto Label PRs #5568: Pull request #14068 opened by sunxxuns

7s

7s

[do not merge] diffusion: support zimage Auto Label PRs #5567: Pull request #14067 opened by yhyang201

10s

10s

Add intel_xpu as backend for GptOssForCausalLM, enabled for bf16 models Auto Label PRs #5566: Pull request #12771 synchronize by ck-intel

8s

8s

Introduce sgl-kernel Dockerfile Auto Label PRs #5565: Pull request #14066 opened by acelyc111

8s

8s

[Minor]Raise Error when deepep num dispatch token per rank is smaller than cuda graph bs Auto Label PRs #5564: Pull request #14065 opened by Fridge003

7s

7s

Fix: fix flashmla fp8 kv cache acc error Auto Label PRs #5563: Pull request #13841 synchronize by whybeyoung

10s

10s

[Feature] Enable PTPC FP8 for compressed tensors moe (aiter kernel) Auto Label PRs #5562: Pull request #12181 synchronize by qichu-yun

8s

8s

Fix: fix flashmla fp8 kv cache acc error Auto Label PRs #5561: Pull request #13841 synchronize by whybeyoung

10s

10s

Fix: fix flashmla fp8 kv cache acc error Auto Label PRs #5560: Pull request #13841 synchronize by whybeyoung

8s

8s

Fix: fix flashmla fp8 kv cache acc error Auto Label PRs #5559: Pull request #13841 synchronize by whybeyoung

8s

8s

NPU Graph Compilation support and PassManager with AddRmsNorm & Quantize fuse. TorchAir compiler backend support. Auto Label PRs #5558: Pull request #11104 synchronize by eshoguli

6s

6s

NPU Graph Compilation support and PassManager with AddRmsNorm & Quantize fuse. TorchAir compiler backend support. Auto Label PRs #5557: Pull request #11104 synchronize by eshoguli

12s

12s

[sgl-kernel][1/2] Fused qk_norm_rope for Qwen3-MoE Auto Label PRs #5556: Pull request #14036 synchronize by yuan-luo

10s

10s

Single Batch Overlap for MoE Models Auto Label PRs #5555: Pull request #9660 synchronize by Sulfur6

9s

9s

support non-disturbing remote-instance-weight-loader Auto Label PRs #5554: Pull request #13125 synchronize by amysaq2023

10s

10s

[apply][2/2] Fused qk_norm_rope for Qwen3-MoE Auto Label PRs #5553: Pull request #13998 synchronize by yuan-luo

10s

10s

Fix: Replace unsafe unwrap in Postgres connector to prevent panic Auto Label PRs #5552: Pull request #14010 synchronize by Yuanjia-Lee

7s

7s

NPU Graph Compilation support and PassManager with AddRmsNorm & Quantize fuse. TorchAir compiler backend support. Auto Label PRs #5551: Pull request #11104 synchronize by OrangeRedeng

10s

10s