01
从 Profiling 到 Simulation：推理性能分析的证据链方法
ai-systems / profiling
profilingsimulationllm-inferenceperformance-analysis
+1
02
GDN 与 Chunked Prefill：为什么 prepare_chunk_indices 会出现在 trace 里
ai-systems / llm-inference
llm-inferencegdnqwen3nextchunked-prefill
+3
03
AWP Profiling API
toolbox
profilingapigpucpu
+2
04
FT vs VLLM vs SGLang 推理框架对比摘要
ai-systems / profiling
profilinginferencertp-llmvllm
+4
05
H20 批量归因分析报告摘要
ai-systems / profiling
profilingh20gpu-kernelcuda
+2
06
AMD MI308X 单卡 Profile 分析摘要（kernel_launch_bound 主导）
ai-systems / profiling
profilingamdmi308xkernel-launch
+2
07
Agentic Infra：LLM 推理性能优化与 GPU 利用率提升
ai-systems / llm-inference
llm-inferencegpu-optimizationprofilingawp
+5
08
Agentic AWP：规模化 Profiling 驱动的 GPU 效率 Breakdown 与能力体系
ai-systems / profiling
awpgpu-profilingbreakdowngpu-efficiency
+3
09
AWP 六维 Breakdown 框架与能力体系摘要
ai-systems / profiling
awpgpu-profilingbreakdowngpu-efficiency
+2
10
LLM 推理性能优化与 GPU 利用率提升摘要
ai-systems / profiling
llm-inferencegpu-optimizationprofilingawp
+3
11
GPU Trace 时间分解与通信计算重叠分析
ai-systems / profiling
GPUProfilingPerformanceDistributed Training
12
Cprof C++ Profiling 核心技术
ai-systems / profiling
profilingperfDWARFeBPF
+2
13
HTA 算法原理与实现
ai-systems / profiling
profilingpytorchgpudistributed-training
+2
14
Critical Path of AI Trace
ai-systems / profiling
AITraceCritical PathGPU
+1