Hacktoberfest 2026:维护者为十月标记出来的 issue,仍然开放、适合新手。 浏览 Hacktoberfest issue

research(KERNEL-CUDA-DECODE-MEGAKERNEL): evaluate tile-scheduled persistent decode

未关闭
#3,084 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
25/100
Issue 类型
功能
描述清晰度
基本清楚
活跃度
活跃
技术栈
cpp

调研方向

首先固定并检查 Cohere 提交 67d0b9ca22ea3652796b715d1d1863459e0e2c3c,然后在 vLLM 和 vllm.cpp 中,通过 ModelRegistry::Forward、dense_attn::AttnBlock、vt::FusedChain 和 vt::MergedGemmGroup,跟踪相同的低批量工作负载。完成的要求是:必须有相对于已固定 vLLM oracle 的 launch、tail、带宽和空闲容量测量证据;只有在证明存在可回收的空闲容量时,才应尝试实现。

由索引模型根据 Issue 内容生成。

描述

Row: KERNEL-CUDA-DECODE-MEGAKERNEL

Evaluate a CUDA decode megakernel that schedules GEMM tiles, attention splits,
and routed-expert work across operation boundaries.

Cohere reports that its North Mini Code engine reaches 292 tok/s at batch size
1 on one H100. The engine reports 1.58x the decode throughput of vLLM v0.24.
The release uses one persistent block per streaming multiprocessor, fixed task
descriptors, counter barriers, and dynamic work queues.

Reference: cohere-ai/cohere-megakernel commit
67d0b9ca22ea3652796b715d1d1863459e0e2c3c.

Scope:

  • Pin and inspect the complete executing path in the Cohere release.
  • Trace an identical low-batch decode workload in vLLM and vllm.cpp.
  • Measure launch gaps, wave tails, device bandwidth, and idle capacity.
  • Specify a CUDA task ABI with descriptors, operation codes, barriers, and
    schedule variants.
  • Build one synthetic persistent-kernel proof if the trace shows recoverable
    idle capacity.
  • Preserve eager and CUDA Graph fallbacks for every unsupported shape.

The pinned vLLM oracle remains the correctness source. The Cohere release is a
performance reference only. Any implementation must route through
ModelRegistry::Forward, dense_attn::AttnBlock, vt::FusedChain, and
vt::MergedGemmGroup where those shared seams apply.

Out of scope:

  • A performance claim before an identical-workload, same-device A/B test.
  • A universal execution model for CPU, ROCm, Metal, Vulkan, or Tenstorrent.
  • Vendoring ThunderKittens before the dependency decision has measured evidence.
  • Treating the BF16 H100 release as completion of required quantized arms.
  • Model integration in the initial spike.

Stop conditions:

  • Stop implementation if the trace does not show material recoverable idle
    capacity after CUDA Graph replay.
  • Leave H100-specific execution PENDING until a leased or otherwise authorized
    H100 can run the gate.
  • Refuse a result if token output differs from the pinned vLLM oracle.

FOLLOWING_AGENTS_PROTOCOL

主要语言
C++
星标
423
派生
53
平均合并
1 天 5 小时
30 天内合并 PR
376

环境准备

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

mudler/vllm.cpp 的其他 Issue

查看 mudler/vllm.cpp 的全部 Issue

相似的 Issue

更多 C++ Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。