dylanyunlong/project_6

Go to file

Claude 730831f267 [fix] paged_attn: re-force V1 — V2 is pure PyTorch, not C++ (confirmed from _custom_ops.py)

Reading _custom_ops.py as input revealed:
  paged_attention_v1 → ixf_F.vllm_single_query_cached_kv_attention (C++ fused kernel)
  paged_attention_v2 → paged_attention_v2_pytorch (pure Python for-loop)

The previous commit incorrectly removed use_v1=True assuming V2 had a C++ backend.
V2 tensor pre-allocation kept for future C++/Triton V2 implementation.
PARTITION_SIZE=1024 change kept (benefits future V2).

2026-08-05 06:27:17 +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

feat: CCCL-derived 3-tier decode dispatch + SM=16 prefill tuning + multi-step scheduling

2026-08-03 08:28:38 +00:00

[perf] MoE intermediate cache pre-allocation: eliminate 189 CUDA mallocs per decode step

2026-08-05 03:58:46 +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

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +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

feat: deploy CCCL-tuned prefix_prefill + muh_dispatch + fix SM=16 count

2026-08-03 08:30:16 +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

feat: deploy CCCL-tuned prefix_prefill + muh_dispatch + fix SM=16 count

2026-08-03 08:30:16 +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

[fix] paged_attn: re-force V1 — V2 is pure PyTorch, not C++ (confirmed from _custom_ops.py)

2026-08-05 06:27:17 +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%