dylanyunlong/project_6

Go to file

dylanyunlon 0154a3b297 fix(tuning_batched_topk): force bits=8, fix SMEM overflow

Previous version used base topk policy's bits (11 for key>=2B),
causing SMEM overflow: 512*4*key_size + 2048*4*batches > 49152.

Fix: force bits=8 (same as radix_sort decision for BI-V100).
SMEM: 512*4*key_size + 256*4*batches = manageable.
Also adds while-loop SMEM check on max_batches.

Detected by test_smem_safety.py: 3 overflows at key_size=2,4,8.

2026-08-01 12:36:57 +08:00

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

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

[muh] kernel_map: full vllm→CCCL mapping with SMEM overflow detection

2026-07-31 11:13:33 +00:00

fix(tuning_batched_topk): force bits=8, fix SMEM overflow

2026-08-01 12:36:57 +08:00

[OPT] BI-V100 Triton kernel tuning + computility-run.yaml optimization

2026-07-30 15:33:44 +00:00

qwen3_6_scripts

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

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

[DEPLOY] Complete submission: baseline + all optimizations

2026-07-30 16:06:20 +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

chat_dataset_v0.json

[DEPLOY] Complete submission: baseline + all optimizations

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

computility-run.yaml

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

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

Dockerfile

[CRITICAL] Enable ixformer native V1/V2 paged attention kernels

2026-07-31 06:18:32 +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

[muh] fix scale_mem_bound: 3 bugs vs CCCL util_arch.cuh

2026-08-01 00:00:02 +08:00

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%