Files

EX Engine 002f9879b2 ref(upstream): FULL TREE — Deep-Spark xllm (1470) + ds_vllm csrc/models (703)

Replaces cherry-picked upstream_ref with complete source trees.

xllm/ — Iluvatar official C++ inference engine (15MB, 1470 files)
  Complete: kernels → layers → models → runtime → scheduler → api
  Excluded: .git, binary images, third_party submodule checkouts

ds_vllm/ — Iluvatar official vllm fork (8MB, 703 files)
  Included: csrc/ (ALL CUDA kernels), fused_moe/, qwen3_5 model, _custom_ops
  Excluded: tests, benchmarks, docs, examples (not needed for reference)

Critical call chains now fully traceable:
  MoE: moe_topk_softmax_kernels.cuh → ixformer.h → fused_moe.cpp → layer
  GDN: qwen3_gated_delta_net_base.cpp → qwen3_5_gated_delta_net.cpp
  Attention: ixformer.h → xllm_paged_attention → attention.cpp

2026-08-10 02:54:03 +00:00

3.5 KiB

Raw Blame History

Disaggregated PD

Background

LLM online inference services typically need to meet two performance metrics: TTFT and TPOT. Traditional Contiguous Batching scheduling strategies mix Prefill and Decode requests during scheduling, causing Prefill and Decode phases to compete for computational resources. This prevents maximized utilization of computing resources and impacts performance metrics. To resolve this conflict, the Prefill and Decode phases are split to run on independent computational resources, enabling parallel execution. This simultaneously reduces TTFT and TPOT while improving throughput.

Introduction

The xLLM PD Separation feature is primarily implemented through the following three modules:

etcd: Stores metadata such as instance information.
xLLM Service: Schedules requests and manages all computing instances.
xLLM: Handles request computation instances.

The overall architecture is shown below:

Usage

Preparation

Install Dependencies

xLLM: Refer to Installation && Compilation
xLLM Service: Refer to PD disaggregation

Obtain Environment Information

Deploying Disaggregated PD Service requires obtaining the Device IP of the machine to create communication resources. Execute the command cat /etc/hccn.conf | grep address on the current AI Server to get the Device IP, for example:

address_0=xx.xx.xx.xx
address_1=xx.xx.xx.xx

address_xx represents the Device IP.

Start Disaggregated PD Service

Start etcd

./etcd

Start xLLM Service

ENABLE_DECODE_RESPONSE_TO_SERVICE=true ./xllm_master_serving --etcd_addr="127.0.0.1:12389" --http_server_port 28888 --rpc_server_port 28889 --tokenizer_path=/path/to/tokenizer_config_dir/

Start xLLM

Taking Qwen2-7B as an example

Start Prefill Instance

/path/to/xllm --model=Qwen2-7B-Instruct \
       --port=8010 \
       --devices="npu:0" \
       --master_node_addr="127.0.0.1:18888" \
       --enable_prefix_cache=false \
       --enable_chunked_prefill=false \
       --enable_disagg_pd=true \
       --instance_role=PREFILL \
       --etcd_addr="127.0.0.1:12389" \
       --transfer_listen_port=26000 \
       --disagg_pd_port=7777 \
       --node_rank=0 \
       --nnodes=1

Start Decode Instance

/path/to/xllm --model=Qwen2-7B-Instruct \
       --port=8020 \
       --devices="npu:1" \
       --master_node_addr="127.0.0.1:18898" \
       --enable_prefix_cache=false \
       --enable_chunked_prefill=false \
       --enable_disagg_pd=true \
       --instance_role=DECODE \
       --etcd_addr="127.0.0.1:12389" \  
       --transfer_listen_port=26100 \
       --disagg_pd_port=7787 \
       --node_rank=0 \
       --nnodes=1

Important notes:

PD disaggregation requires reading the /etc/hccn.conf file. Make sure this file on the physical machine is mapped into the container.
etcd_addr must match the etcd_addr of xllm_service

Notice

Disaggregated PD does not support enabling prefix cache or chunked prefill. These features must be disabled using the following parameters:

--enable_prefix_cache=false  
--enable_chunked_prefill=false

3.5 KiB Raw Blame History