gahow/kvcache-simulator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

KVCache simulator for LLM serving cluster routing research

Browse Source 
Discrete-event simulator for evaluating KV cache-aware routing policies
in prefill-disaggregated LLM serving clusters. Models a two-tier KV cache
hierarchy (L0 GPU HBM + L1 CPU DRAM) with RDMA/PCIe link contention,
architecture-derived roofline compute (MoE, MLA, DSA), and a cluster-wide
meta-store for prefix-aware routing decisions.

Includes 11 routing policies (random, round_robin, least_loaded,
least_tokens, ttl_aware, precise, min_pd, cache_load, cache_score,
estimated_ttft, prefix_affinity), HuggingFace config.json auto-parsing,
built-in GPU hardware presets (H100/H800/H20/A100/B200), and ablation
tooling for systematic policy comparison across real Alibaba serving traces.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Gahow Wang
2026-04-14 01:16:02 +08:00
commit ec73a95e05
52 changed files with 6005 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
.gitmodules vendored Normal file
View File

@@ -0,0 +1,3 @@
[submodule "qwen-bailian-usagetraces-anon"]
path = qwen-bailian-usagetraces-anon
url = https://github.com/alibaba-edu/qwen-bailian-usagetraces-anon.git