01
Engram：TP 分片与同机 DP 共享的源码研究
ai-systems / llm-inference
llm-inferencevllmarchitectureprofiling
+1
02
Engram 预取与 NUMA 放置：从共享页到关键路径
ai-systems / llm-inference
llm-inferencevllmarchitectureprofiling
+1
03
Hyperloom Specialist 与配置调优：一个 Agentic 调参系统的源码拆解
ai-systems / llm-inference
llm-inferencegpu-optimizationagentichyperparameter-tuning
+4
04
vLLM Async Scheduling：三态配置、投机解码与状态提交
ai-systems / llm-inference
llm-inferencevllmdecodekv-cache
+1
05
KV Cache：推理性能的命根子
ai-systems / llm-inference
LLMInferenceKV CachePagedAttention
+2
06
GDN 与 Chunked Prefill：为什么 prepare_chunk_indices 会出现在 trace 里
ai-systems / llm-inference
llm-inferencegdnqwen3nextchunked-prefill
+3
07
Chunked Prefill 深入分析：调度、Chunk Size 与 Attention 形状
ai-systems / llm-inference
llm-inferencechunked-prefillschedulingprefill
+3
08
推理框架对比 2026：从 Engine 到 Serving Stack
ai-systems / llm-inference
vllmsglangtensorrt-llminference-framework
+2
09
批处理与调度：推理服务的灵魂
ai-systems / llm-inference
LLMInferenceBatchingScheduling
+3