Skip to content

GitLab

  • Menu
Projects Groups Snippets
    • Loading...
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in
  • V vllm_cscc
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 0
    • Issues 0
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 0
    • Merge requests 0
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Monitor
    • Monitor
    • Incidents
  • Packages & Registries
    • Packages & Registries
    • Package Registry
    • Infrastructure Registry
  • Analytics
    • Analytics
    • CI/CD
    • Repository
    • Value stream
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • OpenDAS
  • vllm_cscc
  • Repository
  • Branches

  • Overview
  • Active
  • Stale
  • All
  • gy_015-encoder_cache_size merged
    2d940766 · VLLM_ENCODER_CACHE_SIZE控制encoder_cache_size大小 · Mar 24, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.15.1-dev_attn_unified_46f8
    d03e4bf6 · feat(attn): ROCm块大小为64倍数(且不等于64)时走FA varlen_fwd_unified · Mar 19, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.9.2-dev-0316-dp-sbo-deepep-gemm
    6b3bb3ae · sbo-deepep-gemm based on v0.9.2-dev-0316-dp · Mar 18, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.9.2-dev-0316-dp
    236266a9 · [PD]支持dp的分支 · Mar 17, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.9.2-dev
    fb597c49 · Merge branch 'v0.9.2_remove_cpp' into 'v0.9.2-dev' · Mar 13, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • feature/sbo-deep-gemm
    1e2ac05c · add DeepGEMM SBO for DeepEP LL · Mar 12, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.15.1-dev_nmz_glm5
    c5fa1992 · 支持fp8 mqa&&跳过VLLM_USE_FUSED_FILL_RMS_CAT&&跳过load_error · Mar 11, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.15.1-dev_glm5
    3a306316 · feat:修改fp8 mqa接口&&跳过VLLM_USE_FUSED_FILL_RMS_CAT&&跳过load_error · Mar 11, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • gy-0151-mrope-1d
    63132045 · mrope的_get_position修改 · Mar 11, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.15.1-dev_fix_custom_op
    857782c6 · 修复custom_op后端分发问题 · Mar 11, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.15.1-dev-wm-rmsquant
    826f22e1 · 接入siluMulQuant融合 · Mar 06, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.13.0
    0c698cda · adapt to vllm-plugin-FL · Mar 05, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.15.1-dev_rmsnorm_gated_dtype_fix
    4799ca5f · fix: 修复 RMSNormGated 输出类型不一致问题 · Mar 03, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.9.2-dev-pakvcahe
    1ecb8be9 · [PD]类与函数数据结构优化参数调整 && 支持小模型pd推理 · Mar 03, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.15.1-dev_dsa1
    e7096898 · Dsa supported. · Mar 02, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.9.2-torch2.9
    e26f16d0 · remove unused kernel · Feb 26, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.9.2-dev-for-yuanbao
    18341f14 · support fuse cat + q to fp8 + mla · Feb 24, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.15.1-dev_kvpress
    69515892 · docs(issue): 新增 #001 - KV 压缩移植跟踪 · Feb 24, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.9.2-1227-dp
    16f6dfc0 · 解决开启ep mtp>1时cudagraph卡住问题 · Feb 11, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • v0.11.0-dev_tc_opt
    b65d0556 · fix(qwen3): 在 fused RMS+RoPE 算子内支持非连续输入 · Feb 06, 2026
    Compare
    Download source code
    zip tar.gz tar.bz2 tar
  • Prev
  • 1
  • 2
  • 3
  • 4
  • 5
  • Next