SHAOJIE'S BOOK
HomeArchivesCategoriesTagsAbout

Tags

0/1 Adam1
1-bit Adam1
1-bit LAMB1
3FS1
4+1 View Model1
5G1
64bits vs 32bits1
A31
A51
ADR1
ADXL1
AGENTX2
AGRS1
AI10
AI AGENT1
AI Agent1
AI Chip1
AI Cluster1
AI Engineering1
AI INFRA1
AI Infrastructure1
AI STARTUP1
AI Systems1
AIInfra1
AISBench2
AIV7
ALL-TO-ALL1
ALST1
AMAT1
AMD3
APR1
ASCEND4
ASPLOS1
ASTRA-Sim1
ATI1
ATTENTION RESIDUALS1
AVX2
Acceptance Criteria1
Activation Offload1
Agent2
Agent Harness1
Agent Loop1
Agentic RL1
Algorithm1
All-to-All1
AllGather1
Alpha1
Analysis1
Apt1
Architecture Analysis1
Architecture Governance1
Archon1
Ascend12
Ascend 910C1
Ascend 9501
Ascend A51
Ascend C1
Ascend NPU2
AscendCL1
Assembly4
Async2
Async RL1
Attention3
AudioVideo1
AutoResearch1
AutoTP1
Autonomous Driving1
Autotuning1
B2001
BFS1
BHive1
BPMN1
BSHD1
BSND1
BT3
BTL1
Baka Mitai1
Bash1
Benchmark1
Benchmarking1
Big-Endian1
Blackwell1
C5
C++9
CACHE OFFLOADING1
CANN2
CANN VMM2
CCD1
CCX1
CI1
CISC1
CODE WALKTHROUGH1
COMPENSATION1
CONTINUOUS BATCHING1
CP2
CPP1
CPU Thread Socket1
CUDA2
CUDA Allocator1
CUFILE2
CV1
Calling Conventions1
Capability Map1
Career6
Career Strategy1
Checkpoint1
Chunk Layer1
Class2
Claude Code1
CloudMatrix3842
Cloudflare1
ClusterHealthDetect1
Co-design1
Codeforces1
Codex2
Cohousing1
Collective Communication1
Communication1
Communication Logging1
Communication-Compute Fusion1
Compatibility1
Compiler3
Computer Architecture1
Conference1
Context Parallelism1
Crawler2
DDR1
DFD1
DFX3
DFlash2
DIRECT STORAGE2
DISAGGREGATION1
DLP1
DMA3
DNS2
DP3
DPO1
DRAM3
DSA2
DV certificate1
DanceGRPO2
DanceOPD1
Data Lineage1
Data Placement1
DataStates1
Database1
Databases1
Dataset1
Decision Analysis2
Decode1
Deep Learning1
DeepEP1
DeepNVMe1
DeepSeek-R11
DeepSpeed5
Deepfake1
Design Patterns1
DevLog3
DiT1
Diffusion1
Diffusion Language Model1
Diffusion Model1
Digital Worker8
Disk1
Distributed1
Distributed Systems1
Distributed Training2
Domain Model1
Domino1
Domino EP1
DualPath1
Dynamic Programming1
ECC1
EDP1
EP1
ER Model1
ESOP1
ETP1
Echart1
Echo1
Ed2k1
Evals1
Evaluation2
Evidence1
Executable file2
Expert Parallelism4
Explain2
FABRIC MEMORY1
FAST1
FBS1
FLA1
FLOPs Profiler1
FMA1
FP81
FPDT1
FSDP1
FSDP24
Fabric Memory1
FeatureMatrix1
FlashAttention1
FlashInfer1
Flow-Factory1
FlowServe1
Flowchart1
Foundation Model Training1
Frontier Models1
Function Tree1
Functional Decomposition1
FurtherStudy2
GCN1
GDDR6x1
GDN6
GDS3
GIL1
GLIBC1
GLM-52
GLM-5.23
GMM1
GNN1
GNU1
GPT1
GPT-5.61
GPTQ1
GPU1
GPU Benchmark1
GPU DIRECT STORAGE1
GPUDIRECT STORAGE1
GQA1
GRPO4
Game2
Goal1
H1001
H2001
H2D1
HARDWARE-SOFTWARE CO-DESIGN1
HCCL10
HCCS2
HDMI1
HIXL1
HPCAI1
HPL1
HPL-PL1
Hardware Software Co-design1
HiXL1
Hopper1
Housing1
Huawei1
Hugo1
HybridEP1
HyperParallel-MoE1
ILP1
INFERENCE1
INFERENCEX2
IP1
IPC2
IPCC2
IPD2
IPO2
Image1
Inference2
Inference Quantization1
Inference Serving1
Jellyfin1
Jupyter1
KDA3
KIMI3
KV CACHE6
KV Cache5
KVCACHE1
Kavita1
Kernel1
Kernel Launch1
Kimi K31
Knowledge Distillation1
Komga1
Kunpeng3
LATENTMOE1
LDA1
LLM2
LLM Application1
LLM INFERENCE1
LLM Inference2
LLM SERVING5
LLM Serving2
LLM Wiki1
LLaDA1
LONG CONTEXT2
LeetCode1
Leetcode1
LegacyBugs2
Linking1
Live2d1
Lock1
Long Context1
MAC1
MC23
MCA1
MCDA1
MESH NOC1
MFU2
MHA2
MILAN1
MINDIE1
MIPS1
MLA1
MLP1
MOE2
MOONCAKE7
MOPD2
MPI7
MPI option1
MPI_Init1
MPK1
MQA1
MRoPE1
MTE4
MTP2
MULTIMODAL1
MXFP81
Machine Learning4
Marriage1
Matchmaking1
MegaKernel1
MegaMoE1
Megatron3
Megatron Bridge1
Megatron Core1
MemFabric2
Memory Hierarchy1
Memory Optimization1
Memory Semantics4
Mesh Interconnect Architecture1
Metrics1
Micro1
Micro-Fusion1
Micro-architecture1
Microarchitecture4
MindSpeed1
MindSpeed-MM4
MixZ++1
MoE13
MoQ1
Model Compression1
Module1
Money2
Monitor1
MoonEP1
Mount1
Mov-Elimination1
Multi-Agent1
Multimodal1
Multimodal Generation1
Multimodal Model1
Muon1
NAS3
NCCL2
NDS1
NFT1
NLP1
NPU11
NUMA3
NV1
NVIDIA DYNAMO1
NVLink1
Nas2
NoC1
Nvidia5
O21
O32
OPD3
OS1
OSI1
OSS1
Observability1
Omni1
OmniNFT1
Open Source2
OpenCode1
OpenLDAP1
OpenMP1
OpenWRT1
Openssl1
Options4
OutOfOrder1
PAGEDATTENTION2
PCIe1
PD Disaggregation1
PIM2
PKI1
PLMR1
PML1
PP1
PPO1
PPT1
PREFILL-DECODE1
PT2
PTA4
PTX1
PVE1
Pagerank1
Parallel1
Parallelism2
Perf1
Performance3
Performance Engineering1
Performance Model3
Performance Modeling2
Performance Simulation1
Pi1
PicBed1
PicGo2
Pin2
Pipeline1
Post Training1
Post-Training1
PostTraining1
Powershell1
Prefill1
Presentation1
Priority1
Privacy1
Probability Theory1
Product Discovery1
Professional Skills1
Prompt Engineering1
PyG1
PyPTO1
PyTorch3
PyTorch Profiler1
Pytorch9
QAT1
QCC1
QiNiu1
QuantitativeFinance2
Quantization2
Qwen3-Omni1
Qwen3-VL1
Qwen3.55
RAG2
RAID1
RAW1
RDMA9
RGB Lab1
RHLF2
RISC2
RISC-V1
RL30
RLHF1
RLInfra2
RMA1
ROMA1
RTX 30901
Ramulator1
Register-Renaming1
Reinforcement Learning3
Relationship Design1
Reliability Engineering1
Rental1
Reporting2
Requirements Engineering1
Ring Attention1
Risk Management1
RoCE3
RoPE1
RouterReplay1
Rust1
SASS2
SDMA1
SE1
SFT1
SHMEM7
SIMD6
SLIC13
SMA1
SP2
SRAM1
SSD1
SSE1
STEPFUN1
SWAP1
Scaling Law1
Scratchpad1
Sequence Diagram1
Server1
Services1
SimAI1
Simulation1
Skill1
Skylake1
Slurm1
Software Architecture1
SpeculativeDecoding1
Staleness1
Stanford1
State Machine1
Streaming1
Subagent1
SuperPixel1
Survey1
Swimlane Diagram1
System Optimization1
Systemclt1
Systemd1
TCP/IP1
TENSORRT-LLM1
TENT3
TILEXR1
TLB1
TLP1
TND2
TP1
TUTTI1
Team Architecture1
Technical Due Diligence1
Technical Feasibility1
Technical Leadership1
Technology Radar1
Technology Strategy1
Terminal1
Threat Modeling1
Thunderbolt1
TileXR3
Topcoder1
Training1
Training Systems1
TransferQueue2
Transformer1
Transformerless1
Triton4
Type-C1
UB-Mesh1
UBSHMEM1
UDMA4
UPI1
USP2
Ubuntu2
UltraEP1
Ulysses1
Ulysses-Offload2
UniGRPO1
UnifiedBus6
Unreal1
Useful2
VBench1
VEFX-Bench1
VLA1
VLLM4
VLM5
VNC1
VP1
VPN1
VR2
Value Capture1
Value of Information1
VeOmni2
VeRL17
VeRL-Omni2
Vectorization1
Video1
Virtual memory1
Visualization3
Vscode1
Vue1
W8A41
W8A81
WAFER-SCALE1
WAFERLLM1
WAR1
WAW1
WBS1
WLAN1
WQE1
Work Management1
X861
XCCL1
XLA1
XTuner2
Xeon1
ZeRO++1
ZeRO-Offload1
ZenFlow1
Zero-Idiom1
Zsim1
abi1
agent6
ai23
algorithm1
amd3
ampere1
anaconda2
anime4
aocc1
apache1
app1
apple1
apt3
architecture4
arm2
array1
ascend1
assembly2
auto2
avx1
avx2561
bank1
batch1
benchmark2
bilibili1
blog2
broadcast1
bug2
bugs2
business1
c4
c++3
cache2
calloc1
cat2
centos1
chatgpt1
chivier1
chsh1
clang1
clash6
class3
cloud1
clustering1
cmake1
code1
color1
comic2
command1
commands1
compile5
compile options1
compression1
conda1
context switch1
cpp2
cpu3
cpu flags1
crontab1
cs2
css1
ctags1
cuda7
cuobjdump1
dLLM1
ddns1
debug3
deepseek1
diagram1
disassembly1
disk6
display1
dit1
div1
dnat1
dnf1
docker7
docuwiki1
dokuwiki1
domain3
domestic1
dram2
echart1
email1
english1
enter1
entertainment1
epic1
epyc1
ethernet1
family2
filesystem2
firewall1
firewalld1
flags1
flood fill1
focusk1
fork1
forward3
fpic1
fstab1
ftp4
fun98
function call1
game2
gateway1
gcc5
gdb3
gdbgui1
gef1
gem51
gif1
git6
github4
github action1
glibc1
gnu1
go4
golang3
gprof1
gpt1
gpu3
graph1
group1
gzip1
h2652
hash2
header1
health1
heap1
hexo1
home2
homepage6
hpc2
html2
htop2
http1
huawei4
hugo3
hw3
icc1
icecream1
icpc2
incomplete6
inference5
initd1
intel6
interval model1
ip6
ipcc16
iptable1
iptables2
ipv41
ipv62
ispc1
ive1
izone1
j41251
java1
jekyll1
job2
jpg1
k-fold cross validation6
kill1
kpop2
kunpeng 9201
latex2
linux5
live2d1
llm2
llvm8
llvm-mca3
localhost1
logic core1
loop1
lscpu1
lsof2
macbook3
make2
malloc1
manga1
map1
master1
mca5
memory3
micro-op fusions1
minicoda1
mkdocs2
moonlight1
mount1
mpi1
mpicc1
mpiicc1
mtr1
nD-FullMesh1
name1
nas5
nasm1
neon1
network3
networkmanager1
newline1
nginx3
npm1
nsight2
nvidia1
nvprof1
omni2
oneApi1
oneapi1
openmp3
openmpi1
openvpn3
opkg1
optimization1
optimize1
optimizer1
overleaf1
page table1
pam1
paper4
parallel1
password1
pdf1
perf2
piano2
ping1
pip3
png1
podman1
port1
ppt1
prefetch1
price1
process1
profiling1
proxy5
ps1
pull request1
pyc1
pyo1
pypy1
python10
pytorch2
qt1
ram1
ranking1
rar1
rating1
readelf1
reboot2
reduce1
regex1
register2
registers1
report1
route1
router2
rpm1
safety1
scons1
scss1
search bar1
security1
segmentation fault1
server3
sh1
simd1
skill1
slime2
smanga1
smb1
snap1
snat1
sniper1
socket2
speaking1
sql1
sram1
ssh5
ssl2
stack3
stencil1
step-video2
stream2
switch2
synology2
systemctl1
systemd1
t2v6
tar1
tcp1
tcpdump1
terminal1
thread2
tick1
tips1
tlb2
tmm1
tmpfs1
tools2
top3
topology1
torch2
torch.dist1
torch_npu1
torchrun1
traceroute1
uTorrent1
udp1
ufw1
ugreen1
unix1
unravel1
usb1
user1
useradd1
usermod1
vLLM4
vLLM-Ascend1
vLLM-Omni2
vector2
vectorization2
verl2
video3
vim1
virtual machine1
visualization2
vllm4
vlm1
vpn3
vscode1
vscode debug2
vtune3
wake1
warp3
webdav1
website4
wget1
wifi1
windows3
wireguard5
wireshark1
wlt1
wonyoung1
workflow1
x111
x863
xDMA1
xDeepServe1
youtube1
yum1
yun1
zen22
zero-idioms1
zip1
zsh1
zsim2
Shaojie Tan

Shaojie Tan

๐˜Š๐˜ฐ๐˜ฎ๐˜ฑ๐˜ถ๐˜ต๐˜ฆ๐˜ณ ๐˜ˆ๐˜ณ๐˜ค๐˜ฉ๐˜ช๐˜ต๐˜ฆ๐˜ค๐˜ต๐˜ถ๐˜ณ๐˜ฆ & ๐˜๐˜—๐˜Š

Anhui, Hefei, China

Posts

617

Categories

51

Tags

941

Follow

Categories

  • 0-hardwareSoftwareCodesign1
  • 1-AI Model Architecture3
    • 0-TOP1
  • 1-AI Systems35
    • 0-TOP2
  • 1-AIV3
  • 1-Agent Workflow9
    • 0-TOP3
  • 1-Distributed Parallelism8
  • 1-GeneralSkills2
  • 1-Infer7
  • 1-Operator Development7
  • AI6
  • Algorithms12
  • Architecture42
  • Artificial Intelligence74
    • 1-Distributed Parallelism1
  • Camp1
  • Databases2
  • HPC1
  • Math2
  • Network8
  • OOW37
    • 0-TOP1
  • Operating system8
  • Overview16
  • Programming44
  • ProjectRecord3
  • Software1
  • Thinking13
  • Tips9
  • Treasure1
  • Tutorials119
  • Values2
  • Work1
  • architecture2
  • diary4
  • english4
  • hardware2
  • love1
  • math3
  • network19
  • operating system5
  • programming1
  • security3
  • software23
  • thinking9
    • OOW1
  • tips5
  • toLearn56
  • values2

Subscribe for updates

follow.it

Links

  • ibugsibug.io
  • jiegecjia.je
  • leimaoleimao.github.io

Recents

2027-03-15

Building Large-Scale AI Systems on Ascend: Training, Inference, and Multimodal Optimization

Overview

2026-08-27

Mooncake TENT Request Path

1-Infer

2026-08-27

Ascend Data Movement Evolution

1-AI Systems

2026-08-27

Ascend Communication Axes

1-AI Systems

2026-08-27

Scratchpad and NoC

Architecture

Archives

  • March 20271
  • August 202641
  • July 202638
  • June 20269
  • May 202613
  • April 20267
  • March 20262
  • February 20267
  • January 20267
  • December 202518
  • November 20256
  • October 20251
  • September 20252
  • May 20255
  • April 20251
  • March 20254
  • February 20255
  • January 20254
  • December 20245
  • November 20241
  • October 20245
  • September 202411
  • August 20243
  • July 20244
  • June 20241
  • May 20242
  • April 20248
  • March 20243
  • February 20241
  • January 202414
  • December 202321
  • November 202333
  • October 202358
  • September 202337
  • August 202323
  • July 202324
  • June 202313
  • May 202319
  • April 20239
  • March 20235
  • February 20232
  • January 20236
  • December 20222
  • November 20224
  • October 20225
  • September 20224
  • August 20228
  • July 20227
  • June 20227
  • May 202210
  • April 20225
  • March 20227
  • February 20222
  • January 20225
  • December 20214
  • November 20212
  • October 202114
  • September 202111
  • August 202113
  • July 202128

Tags

0/1 Adam1
1-bit Adam1
1-bit LAMB1
3FS1
4+1 View Model1
5G1
64bits vs 32bits1
A31
A51
ADR1
ADXL1
AGENTX2
AGRS1
AI10
AI AGENT1
AI Agent1
AI Chip1
AI Cluster1
AI Engineering1
AI INFRA1
SHAOJIE'S BOOK

© 2026 Shaojie Tanย ย Powered by Hexoย &ย Icarus

ยฉ 2019

ร—