Gahow Wang
ec73a95e05
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>
42 lines
1.0 KiB
JSON
42 lines
1.0 KiB
JSON
{
|
|
"architectures": [
|
|
"Qwen3MoeForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 151643,
|
|
"decoder_sparse_step": 1,
|
|
"eos_token_id": 151645,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 6144,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 8192,
|
|
"max_position_embeddings": 262144,
|
|
"max_window_layers": 28,
|
|
"mlp_only_layers": [],
|
|
"model_type": "qwen3_moe",
|
|
"moe_intermediate_size": 2560,
|
|
"norm_topk_prob": true,
|
|
"num_attention_heads": 96,
|
|
"num_experts": 160,
|
|
"num_experts_per_tok": 8,
|
|
"num_hidden_layers": 62,
|
|
"num_key_value_heads": 8,
|
|
"output_router_logits": false,
|
|
"qkv_bias": false,
|
|
"rms_norm_eps": 1e-06,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000000,
|
|
"router_aux_loss_coef": 0.0,
|
|
"shared_expert_intermediate_size": 0,
|
|
"sliding_window": null,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.52.4",
|
|
"use_cache": true,
|
|
"use_qk_norm": true,
|
|
"use_sliding_window": false,
|
|
"vocab_size": 151936
|
|
}
|