Skip to content
vLLM Ascend
support_matrix
Initializing search
vllm-project/vllm-ascend
Home
Getting Started
User Guide
Developer Guide
Community
vLLM Ascend
vllm-project/vllm-ascend
Home
Getting Started
Getting Started
Overview
Quick Start
Installation
Model Tutorials
Model Tutorials
Qwen3-Dense
Qwen-VL-Dense
Qwen3-30B-A3B
Qwen3-235B-A22B
Qwen3-VL-30B-A3B-Instruct
Qwen3-VL-235B-A22B-Instruct
Qwen3-Coder-30B-A3B
Qwen3-Embedding
Qwen3-VL-Embedding
Qwen3-Reranker
Qwen3-VL-Reranker
Qwen3-Next
Qwen3-Omni-30B-A3B-Thinking
Qwen3.5-27B & Qwen3.6-27B
Qwen3.5-Dense (2B/4B/9B)
Qwen3.5-397B-A17B
Qwen3.6-35B-A3B
DeepSeek-V3.1
DeepSeek-V3.2
DeepSeek-V4-Flash
DeepSeek-V4-Pro
DeepSeek-R1
DeepSeekOCR2
GLM-4.x
GLM-5
GLM-5.2
Kimi-K2-Thinking
Kimi-K2.5
Kimi-K2.6
PaddleOCR-VL
MiniMax-M2
Hunyuan-A13B-Instruct
Hy3-preview
Minitron-8B-Base
LLaVA-OneVision-Qwen2-0.5B-OV
gpt-oss-120b
Mixtral-8x7B-Instruct-v0.1
Qwen3-ASR-1.7B
Qwen2.5-Math-RM-72B
InternVL3.5
Feature Tutorials
Feature Tutorials
PD Colocated (Mooncake, Multi-Instance)
PD Disaggregation (Mooncake, Single Node)
PD Disaggregation (Mooncake, Multi Node)
Dynamic Chunked Pipeline Parallel
Suffix Speculative Decoding
Ray
FAQs
User Guide
User Guide
Features and Models
Features and Models
Supported Models
Supported Features
Feature Matrix
Configuration
Configuration
Environment Variables
Additional Configuration
Feature Guide
Feature Guide
Graph Mode
CPU Binding
AI QoS
Quantization
Sleep Mode
Structured Output
LoRA
Expert Parallelism Load Balancer
NetLoader
RFork
EPD Disaggregation
KV Pool
KV Cache CPU Offload
Recompute CPU Offload Guide
Large Scale EP
UCM Deployment
Fine-grained TP
Speculative Decoding
Context Parallel
Sequence Parallelism
Batch Invariance
LMCache Ascend Deployment
Dynamic Chunk Pipeline Parallel
Flash Attention
ShortRequestFirst Prefill Scheduling
Batch-Job-Aware Scheduler
Deployment Guide
Deployment Guide
Using Volcano Kthena
Using MindIE Motor
Release Notes
Developer Guide
Developer Guide
Contribution
Contribution
Testing
Doc Writing
Multi-Node Test
Nightly CI Test
E2E CI Test
Design Documents
Design Documents
Patch
CPU Binding
ModelRunner Prepare Inputs
Disaggregated Prefill
EPLB Swift Balancer
ACL Graph
KV Cache Pool Guide
Add Custom ACLNN Op
Context Parallel
Balance Schedule Refactor
Dynamic Chunked Pipeline Parallel
Quantization
NPUGraph Ex
Evaluation
Evaluation
Using EvalScope
Using lm_eval
Using AISBench
Using OpenCompass
Performance and Debug
Performance and Debug
Performance Benchmark
Optimization and Tuning
Service Profiling Guide
msprobe Guide
Community
Community
Governance
Contributors
Issue Workflow Guidelines
Slash Commands
Versioning Policy
User Stories
User Stories
LLaMA-Factory
support_matrix
¶
This section provides a detailed matrix supported by vLLM Ascend.
Back to top