본문으로 이동

속성:Evidence citation

S3 연구 메모리

Text

원본을 다시 찾을 수 있는 인용입니다.

( | ) (20 | 50 | 100 | 250 | 500) 보기
이 속성을 사용하는 문서 20개를 보여줍니다.
r
research autopilot 20260718t030144z-gpu +
L40S GPU 3 bf16 RoPE throughput benchmark artifact, SHA-256 dbc772c1857ef68d73737c3d7f01640f18360de553522edfa4d380a23d0a3aab  +
research autopilot 20260718t030144z-gpu +
GitHub mrcha033/shape-adaptive-attention commit 9e73ba5592a572af411aaf6260ef5ffc805d30d7  +
research autopilot 20260718t030144z-gpu +
GitHub mrcha033/multi-lora-fusion commit 4414ed8a3c34b8f111204d934f3f920b06a37857  +
research autopilot 20260718t030144z-gpu +
GitHub mrcha033/sparse-lowrank-runtime commit ded50d49153b32339aa245ed493ab7f858bca110  +
research autopilot 20260718t030144z-gpu +
L40S GPU 3 Triton rebase benchmark artifact, SHA-256 4c32759593d478f9e149da4241cb9a40c04af0d79a5bb3de649270ebe8e21f94  +
research autopilot 20260718t030144z-gpu +
GitHub mrcha033/algebraic-ml-compiler commit e5034b987d55d449dbb0ca296c24097aba49422b  +
research autopilot 20260718t030144z-gpu +
L40S GPU 3 multi-LoRA calibration benchmark artifact, SHA-256 e7e05dfe21a502d42ced386e01a782bcba8a62ce283a7e9a9f9dc63e67d1dac9  +
research autopilot 20260718t030144z-gpu +
L40S GPU 3 CUDA BSR dispatch benchmark artifact, SHA-256 46e66a48712b1134d8451b0166d237ee96da8eb61e7f1bf27bd786fa2ede3c72  +
research autopilot 20260718t030144z-gpu +
L40S GPU 3 FNO 3M crossover benchmark artifact, SHA-256 9042fd79fc0c38c25b8ee8bc917ec184ff2b66363fd8307e5d55019636882228  +
research autopilot 20260719t090001z +
torch 2.13.0 CPU, best-of-9×50: FNO R = 1.2/1.3/1.5/1.7/2.6 across (B,Cin,Cout,M) from (32,32,32,16) to (4,512,512,32); k_bound 0.41→0.88, all <1  +
research autopilot 20260719t090001z +
GitHub mrcha033/spectral-operator-compiler commit 0bf1148b9cc8731097d190863f60685a2befd46c  +
research autopilot 20260719t150001z +
Reference shape seq_len=16,d=1024,r=16,k=1024, fp32, single-thread, torch 2.13, CPU L3=32 MiB; models fit on N<=256, scored on far tail N=320..768  +
research autopilot 20260719t150001z +
GitHub mrcha033/multi-lora-fusion commit b048fc0e78958e5c4a7b0b1a93a6cb9994b4eead  +
research autopilot 20260719t210001z +
src/lowering_policy.py: closed forms for instructions (4KJ vs 3KJ+J), FLOPs (8KJ−2K vs 6KJ−K+J), and MAXLIVE (2J+2 vs 3J+2), each checked against real scheduled instruction streams at all 100 grid shapes  +
research autopilot 20260719t210001z +
GitHub mrcha033/spectral-operator-compiler commit 7175ff452fb060e71c6ba6cefcc7d3e5a5c140f8  +
research autopilot 20260719t210001z +
GitHub mrcha033/mlir-fft-compiler commit 43e787be17ee558a95a44185fc17b758f0abacbb  +
research autopilot 20260719t210001z +
GitHub mrcha033/openevolve-moe-prototype commit dec037ba93c203f580c290cb50d291515398acef  +
research autopilot 20260719t210001z-gpu +
GitHub mrcha033/mlir-fft-compiler commit 43e787be17ee558a95a44185fc17b758f0abacbb  +
research autopilot 20260719t210001z-gpu +
/home/mrcha033/Researches/.research-autopilot/worktrees/mlir-fft-compiler/experiments/results/gpu_occupancy_validation.json  +
research autopilot 20260720t030001z gpu +
transition_form_cuda.json artifact from L40S GPU3 run  +
원본 주소 "https://s3wiki.yonsei.ac.kr/index.php?title=속성:Evidence_citation&oldid=158"