dylanyunlong/project_6

Go to file

muh-bot 5e618bf480 [housekeeping] add enginex_base/ to gitignore — 解压后的基础引擎仅供本地分析

基础引擎结构 (排除 pkgs 预编译包):
  顶层: Dockerfile, computility-run.yaml, paged_attn.py, prefix_prefill.py, attention.py
  qwen3_6_scripts/: 我们的全部适配代码 (模型定义, attention, API, parsers, patches)
  vllm/: vllm 0.6.3 BI-V100 适配版 (985 files)
    _custom_ops.py: ixformer 绑定层 (V1 decode, silu_and_mul, rms_norm...)
    attention/selector.py: backend 选择 (BI-V100 → XFORMERS → _run_sdpa_fallback)
    model_executor/models/: 200+ 模型定义 (无 qwen3_5)

关键发现:
  1. 基础引擎 Dockerfile 只有 4 行: FROM + COPY + RUN patch_ops.sh
  2. vllm/_custom_ops.py 硬编码 SMEM=32KB (已在我们版本修为 49152)
  3. attention selector: BI-V100 → XFORMERS (not FlashAttn, SM<80)
  4. Prefill 路径: xformers._run_sdpa_fallback (PyTorch matmul+softmax)
     不是 paged_attn.forward_prefix (那是 context attention for cached tokens)

CCCL source read: dispatch_batch_memcpy.cuh (large_buffer vs small_buffer paths)
  KV block size = 16×4×256×2 = 32KB → large_buffer path in CCCL

2026-08-05 07:17:37 +00:00

[CCCL] 瘦身 + 补全: 移除 cudax/python/libcudacxx-tests 冗余文件, 新增 c2h 测试助手 + cmake 构建系统 + 8 个 CUDA thrust examples

2026-08-03 12:39:26 +00:00

[analysis] MoE execution path: 640+ kernel launches/step, 192 CUDA mallocs/step

2026-08-05 03:58:07 +00:00

[gen_patch] Replace dead .cu injection points with real Triton/config targets

2026-08-05 03:36:37 +00:00

fix: critical config + tuning corrections from CCCL source analysis

2026-08-03 06:45:54 +00:00

qwen3_6_scripts

[CRITICAL] Restore original enginex paged_attn.py — Triton kernel hangs BI-V100

2026-08-05 07:11:59 +00:00

[perf] sampler: fast path for top_k without top_p — torch.topk replaces full sort

2026-08-05 06:32:35 +00:00

feat: add qwen3_5.py vllm adapter for Qwen3.6-35B-A3B

2026-08-01 13:54:33 +00:00

__init__.py

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +00:00

.gitignore

[housekeeping] add enginex_base/ to gitignore — 解压后的基础引擎仅供本地分析

2026-08-05 07:17:37 +00:00

attention.py

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +00:00

baseline.muh

[MUH] Fix three-layer disconnect — C++ headers are now the single source of truth

2026-07-30 14:12:33 +00:00

BI_V100_BENCHMARK_RUNBOOK.md

[docs] BI-V100 benchmark runbook: Phase 0 硬件探测 + Phase 1 quick sweep + Phase 3 端到端验证

2026-08-04 01:14:30 +00:00

CCCL_INTEGRATION_STATUS.md

docs: CCCL integration status — 462 assets inventory, 8/8 decode hot path coverage, no-clone-more verdict

2026-08-03 03:50:24 +00:00

chat_dataset_v0.json

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +00:00

computility-run.yaml

[yaml+prefill] num-scheduler-steps 8→16 from CCCL delay analysis

2026-08-05 03:16:06 +00:00

Dockerfile

[SIMPLIFY] Dockerfile 恢复到基础引擎原版 4 行——所有适配通过 patch_ops.sh

2026-08-05 07:14:23 +00:00

ENGINEX_INJECTION_MAP.md

docs: EngineX vllm injection map — Python not C++, Triton not CUDA, 32KB SMEM claim

2026-08-03 03:59:49 +00:00

enginex-vllm-bi100-qwen36-main.zip

update baseline

2026-07-30 15:19:37 +00:00

launch_service

sync: align with enginex-vllm-bi100-qwen36 baseline (1902c81f)

2026-07-31 09:43:58 +00:00

muh_dispatch.py

[muh_dispatch] 修正 head_dim=128→256 + 删除死代码 + 强制 V1

2026-08-05 07:12:26 +00:00

muh_kernel_map.py

[docs+code] lookback delay is a no-op on BI-V100 + V2 compound reduce pattern

2026-08-05 03:35:07 +00:00

MUH_PROJECT_CHECKPOINT.md

[MUH] Fix 7 structural discrepancies vs CCCL — read source, not grep

2026-07-30 14:37:38 +00:00

paged_attention_v2_pytorch.py

[v2] document CCCL kernel_reduce.cuh SingleTile + scan GridThreshold=500 insights

2026-08-05 03:57:29 +00:00

paged_attention_v2_triton.py

[ARCH] CCCL-derived paged attention kernel architecture + Triton rewrite

2026-07-31 04:13:07 +00:00

paged_attn.py

[CRITICAL] Restore original enginex paged_attn.py — Triton kernel hangs BI-V100

2026-08-05 07:11:59 +00:00

prefix_prefill.py

[prefill] asymmetric BLOCK_M/BLOCK_N from CCCL AgentReduce insight

2026-08-05 03:07:20 +00:00

README.md

Initial commit

2026-07-30 17:03:23 +08:00

TUNING_SURFACE_TRUTH.md

fix: revert invalid patches, add honest tuning surface assessment

2026-08-03 10:34:28 +00:00

README.md

project_6

Languages

C++ 41.8%

Cuda 31.6%

Python 22.2%

C 2.1%

CMake 1.1%

Other 1.1%