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

vLLM oracle: GPU page fault in ROCm Triton paged-attention fallback (Qwen3.5 GDN, IQ3_XXS, gfx1200)

未关闭
  • 哪里不对？
#3,167 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
32/100
Issue 类型
缺陷
描述清晰度
需要澄清
活跃度
活跃
技术栈
cpp, docker
领域
backend, machine-learning, performance

调研方向

阅读 .agents/oracles/vllm-gguf-plugin.md，并复现其中描述的固定 ROCm/gfx1200 设置。使用 AMD_LOG_LEVEL/ROCM_DEBUG，然后在可能的情况下，将失败缩减为更小的 Triton 级别复现。完成的标准是确定一个可复现的内核级原因或最小化复现；在该组合输出一个 token 之前，保持 gateable = no。

由索引模型根据 Issue 内容生成。

描述

Row: -

Found running ORACLE-VLLM-ROCM-GFX1200-DOCKER (#2961), against the pinned
vLLM oracle (e126687a9a8, ROCm/gfx1200, RX 9060 XT), loading
unsloth/Qwen3.8-27B-GGUF:UD-IQ3_XXS (a Qwen3.5-family Gated-Delta-Net
architecture) plus its mmproj-F16.gguf.

With language_model_only=True (skips multimodal dummy-data profiling) and
enforce_eager=True (skips CUDA-graph capture, whose own "minimal"
profiling KV buffer OOMs independently -- see the row's spec, ## Risks,
for that separate finding), model loading and KV-cache sizing both complete
successfully:

Available KV cache memory: 0.84 GiB
GPU KV cache size: 5,802 tokens, Maximum concurrency for 4,096 tokens per request: 1.42x
Free memory on device (15.82/15.92 GiB) on startup. ... Actual usage is 12.11 GiB
for consumed memory (weights + non-torch), 1.38 GiB for peak activation, and 0.0 GiB
for CUDAGraph memory.

Then, on the very next step:

WARNING [chunked_prefill_paged_decode.py:433] Cannot use ROCm custom paged attention
kernel, falling back to Triton implementation.
Memory access fault by GPU node-1 (Agent handle: 0x247ec020) on address 0x7f229fb44000.
Reason: Page not present or supervisor privilege.

This is a raw HIP-level trap -- no Python traceback names a line, and no
token is ever produced. This is vLLM's/Triton's own ROCm kernel dispatch,
not vllm.cpp code, so it is not fixed in the same flow here; root-causing
a page fault with no Python-level stack needs its own investigation
(AMD_LOG_LEVEL/ROCM_DEBUG, or reducing to a smaller Triton-level repro
off the full 27B model) rather than a guess landed in a hurry. Filed so
.agents/oracles/vllm-gguf-plugin.md has something concrete to point at
when it records this device: this combination has never emitted a token on
gfx1200, which is exactly the fact that keeps that file's gateable = no
correct rather than stale.

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。