dylanyunlong/project_6

Go to file

Claude 95d872e8f5 feat(muh): scan_by_key 53→284 lines — full key_size×val_size type dispatch

From 1KB/53 lines (59× compression vs CCCL 85KB) to 284 lines:
- Add 16 type specialization structs (key_size=1,2,4,8 × val_size=1,2,4,8)
- SM=16 tile maximization: k4_v4 (attention hot path) 30720→49152 (62%→100% SMEM)
- SM=16 tile increases across all small pairs (k1_v1: 3072→12288, k2_v1: 6144→15360)
- Delay halved for L2=6MB: fixed_delay values /2 (less inter-CTA contention)
- Proper CCCL-matching ScanByKeyPolicy struct with ScanByKeyAlgorithm enum
- SMEM-safe fallback with dynamic items computation from pair_size
- Macro-based dispatch (MK_POLICY) for clean type selection

2026-08-03 07:18:23 +00:00

[INFRA] Import NVIDIA/CCCL upstream as optimization reference library

2026-07-30 09:35:51 +00:00

docs: CCCL → Triton methodology transfer — parameter search translation table

2026-08-03 04:37:23 +00:00

feat(muh): scan_by_key 53→284 lines — full key_size×val_size type dispatch

2026-08-03 07:18:23 +00:00

fix: critical config + tuning corrections from CCCL source analysis

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

qwen3_6_scripts

fix: critical config + tuning corrections from CCCL source analysis

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

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +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

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

fix: dial back max-num-seqs 256→8, revert batched-tokens and mem-util

2026-08-03 06:51:33 +00:00

Dockerfile

fix: critical config + tuning corrections from CCCL source analysis

2026-08-03 06:45:54 +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

refactor(muh_dispatch): read-once from C++ headers, not write-twice

2026-08-01 01:30:42 +08:00

muh_kernel_map.py

fix(hardware): SM count 50→16 confirmed on Phanthy Cloud BI-V100

2026-08-01 13:39:28 +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

[FIX] V2 shape mismatch bug — v_padded used num_heads for kv_h tensor

2026-07-31 03:52:23 +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

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

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

prefix_prefill.py

[DEPLOY] Complete submission: baseline + all optimizations

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

README.md

Initial commit

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

README.md

project_6

Languages

C++ 41.8%

Cuda 31.6%

Python 22.2%

C 2.1%

CMake 1.1%

Other 1.1%