Skip to content

[0.13.0] modify release note & supported matrix #6751

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wangxiyuan merged 1 commit into from
Feb 14, 2026
Merged

[0.13.0] modify release note & supported matrix #6751

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
32 changes: 16 additions & 16 deletions docs/source/user_guide/release_notes.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,31 +7,31 @@ This is the final release of v0.13.0 for vLLM Ascend. Please follow the [officia
### Highlights

**Model Support**
- **DeepSeek-R1 & DeepSeek-V3.2**: Performance optimizations, and async scheduling enhancements. [#3631](https://github.com/vllm-project/vllm-ascend/pull/3631) [#3900](https://github.com/vllm-project/vllm-ascend/pull/3900) [#3908](https://github.com/vllm-project/vllm-ascend/pull/3908) [#4191](https://github.com/vllm-project/vllm-ascend/pull/4191) [#4805](https://github.com/vllm-project/vllm-ascend/pull/4805)
- **Qwen3-Next**: Full support for Qwen3-Next series including 80B-A3B-Instruct with full graph mode, MTP, quantization (W8A8), NZ optimization, and chunked prefill. Fixed multiple accuracy and stability issues. [#3450](https://github.com/vllm-project/vllm-ascend/pull/3450) [#3572](https://github.com/vllm-project/vllm-ascend/pull/3572) [#3428](https://github.com/vllm-project/vllm-ascend/pull/3428) [#3918](https://github.com/vllm-project/vllm-ascend/pull/3918) [#4058](https://github.com/vllm-project/vllm-ascend/pull/4058) [#4245](https://github.com/vllm-project/vllm-ascend/pull/4245) [#4070](https://github.com/vllm-project/vllm-ascend/pull/4070) [#4477](https://github.com/vllm-project/vllm-ascend/pull/4477) [#4770](https://github.com/vllm-project/vllm-ascend/pull/4770)
- **DeepSeek-R1 & DeepSeek-V3.2**: [Experimental]Performance optimizations, and async scheduling enhancements. [#3631](https://github.com/vllm-project/vllm-ascend/pull/3631) [#3900](https://github.com/vllm-project/vllm-ascend/pull/3900) [#3908](https://github.com/vllm-project/vllm-ascend/pull/3908) [#4191](https://github.com/vllm-project/vllm-ascend/pull/4191) [#4805](https://github.com/vllm-project/vllm-ascend/pull/4805)
- **Qwen3-Next**: [Experimental]Full support for Qwen3-Next series including 80B-A3B-Instruct with full graph mode, MTP, quantization (W8A8), NZ optimization, and chunked prefill. Fixed multiple accuracy and stability issues. [#3450](https://github.com/vllm-project/vllm-ascend/pull/3450) [#3572](https://github.com/vllm-project/vllm-ascend/pull/3572) [#3428](https://github.com/vllm-project/vllm-ascend/pull/3428) [#3918](https://github.com/vllm-project/vllm-ascend/pull/3918) [#4058](https://github.com/vllm-project/vllm-ascend/pull/4058) [#4245](https://github.com/vllm-project/vllm-ascend/pull/4245) [#4070](https://github.com/vllm-project/vllm-ascend/pull/4070) [#4477](https://github.com/vllm-project/vllm-ascend/pull/4477) [#4770](https://github.com/vllm-project/vllm-ascend/pull/4770)
- **InternVL**: Added support for InternVL models with comprehensive e2e tests and accuracy evaluation. [#3796](https://github.com/vllm-project/vllm-ascend/pull/3796) [#3964](https://github.com/vllm-project/vllm-ascend/pull/3964)
- **LongCat-Flash**: Added support for LongCat-Flash model. [#3833](https://github.com/vllm-project/vllm-ascend/pull/3833)
- **minimax_m2**: Added support for minimax_m2 model. [#5624](https://github.com/vllm-project/vllm-ascend/pull/5624)
- **Whisper & Cross-Attention**: Added support for cross-attention and Whisper models. [#5592](https://github.com/vllm-project/vllm-ascend/pull/5592)
- **Pooling Models**: Added support for pooling models with PCP adaptation and fixed multiple pooling-related bugs. [#3122](https://github.com/vllm-project/vllm-ascend/pull/3122) [#4143](https://github.com/vllm-project/vllm-ascend/pull/4143) [#6056](https://github.com/vllm-project/vllm-ascend/pull/6056) [#6057](https://github.com/vllm-project/vllm-ascend/pull/6057) [#6146](https://github.com/vllm-project/vllm-ascend/pull/6146)
- **PanguUltraMoE**: Added support for PanguUltraMoE model. [#4615](https://github.com/vllm-project/vllm-ascend/pull/4615)
- **LongCat-Flash**: [Experimental]Added support for LongCat-Flash model. [#3833](https://github.com/vllm-project/vllm-ascend/pull/3833)
- **minimax_m2**: [Experimental]Added support for minimax_m2 model. [#5624](https://github.com/vllm-project/vllm-ascend/pull/5624)
- **Whisper & Cross-Attention**: [Experimental]Added support for cross-attention and Whisper models. [#5592](https://github.com/vllm-project/vllm-ascend/pull/5592)
- **Pooling Models**: [Experimental]Added support for pooling models with PCP adaptation and fixed multiple pooling-related bugs. [#3122](https://github.com/vllm-project/vllm-ascend/pull/3122) [#4143](https://github.com/vllm-project/vllm-ascend/pull/4143) [#6056](https://github.com/vllm-project/vllm-ascend/pull/6056) [#6057](https://github.com/vllm-project/vllm-ascend/pull/6057) [#6146](https://github.com/vllm-project/vllm-ascend/pull/6146)
- **PanguUltraMoE**: [Experimental]Added support for PanguUltraMoE model. [#4615](https://github.com/vllm-project/vllm-ascend/pull/4615)

**Core Features**
- **Context Parallel (PCP/DCP)**: [Experimental] Added comprehensive support for Prefill Context Parallel (PCP) and Decode Context Parallel (DCP) with ACLGraph, MTP, chunked prefill, MLAPO, and Mooncake connector integration. This is an experimental feature - feedback welcome. [#3260](https://github.com/vllm-project/vllm-ascend/pull/3260) [#3731](https://github.com/vllm-project/vllm-ascend/pull/3731) [#3801](https://github.com/vllm-project/vllm-ascend/pull/3801) [#3980](https://github.com/vllm-project/vllm-ascend/pull/3980) [#4066](https://github.com/vllm-project/vllm-ascend/pull/4066) [#4098](https://github.com/vllm-project/vllm-ascend/pull/4098) [#4183](https://github.com/vllm-project/vllm-ascend/pull/4183) [#5672](https://github.com/vllm-project/vllm-ascend/pull/5672)
- **Full Graph Mode (ACLGraph)**: Enhanced full graph mode with GQA support, memory optimizations, unified logic between ACLGraph and Torchair, and improved stability. [#3560](https://github.com/vllm-project/vllm-ascend/pull/3560) [#3970](https://github.com/vllm-project/vllm-ascend/pull/3970) [#3812](https://github.com/vllm-project/vllm-ascend/pull/3812) [#3879](https://github.com/vllm-project/vllm-ascend/pull/3879) [#3888](https://github.com/vllm-project/vllm-ascend/pull/3888) [#3894](https://github.com/vllm-project/vllm-ascend/pull/3894) [#5118](https://github.com/vllm-project/vllm-ascend/pull/5118)
- **Full Graph Mode (ACLGraph)**: [Experimental]Enhanced full graph mode with GQA support, memory optimizations, unified logic between ACLGraph and Torchair, and improved stability. [#3560](https://github.com/vllm-project/vllm-ascend/pull/3560) [#3970](https://github.com/vllm-project/vllm-ascend/pull/3970) [#3812](https://github.com/vllm-project/vllm-ascend/pull/3812) [#3879](https://github.com/vllm-project/vllm-ascend/pull/3879) [#3888](https://github.com/vllm-project/vllm-ascend/pull/3888) [#3894](https://github.com/vllm-project/vllm-ascend/pull/3894) [#5118](https://github.com/vllm-project/vllm-ascend/pull/5118)
- **Multi-Token Prediction (MTP)**: Significantly improved MTP support with chunked prefill for DeepSeek, quantization support, full graph mode, PCP/DCP integration, and async scheduling. MTP now works in most cases and is recommended for use. [#2711](https://github.com/vllm-project/vllm-ascend/pull/2711) [#2713](https://github.com/vllm-project/vllm-ascend/pull/2713) [#3620](https://github.com/vllm-project/vllm-ascend/pull/3620) [#3845](https://github.com/vllm-project/vllm-ascend/pull/3845) [#3910](https://github.com/vllm-project/vllm-ascend/pull/3910) [#3915](https://github.com/vllm-project/vllm-ascend/pull/3915) [#4102](https://github.com/vllm-project/vllm-ascend/pull/4102) [#4111](https://github.com/vllm-project/vllm-ascend/pull/4111) [#4770](https://github.com/vllm-project/vllm-ascend/pull/4770) [#5477](https://github.com/vllm-project/vllm-ascend/pull/5477)
- **Eagle Speculative Decoding**: Eagle spec decode now works with full graph mode and is more stable. [#5118](https://github.com/vllm-project/vllm-ascend/pull/5118) [#4893](https://github.com/vllm-project/vllm-ascend/pull/4893) [#5804](https://github.com/vllm-project/vllm-ascend/pull/5804)
- **PD Disaggregation**: Set ADXL engine as default backend for disaggregated prefill with improved performance and stability. Added support for KV NZ feature for DeepSeek decode node. [#3761](https://github.com/vllm-project/vllm-ascend/pull/3761) [#3950](https://github.com/vllm-project/vllm-ascend/pull/3950) [#5008](https://github.com/vllm-project/vllm-ascend/pull/5008) [#3072](https://github.com/vllm-project/vllm-ascend/pull/3072)
- **KV Pool & Mooncake**: Enhanced KV pool with Mooncake connector support for PCP/DCP, multiple input suffixes, and improved performance of Layerwise Connector. [#3690](https://github.com/vllm-project/vllm-ascend/pull/3690) [#3752](https://github.com/vllm-project/vllm-ascend/pull/3752) [#3849](https://github.com/vllm-project/vllm-ascend/pull/3849) [#4183](https://github.com/vllm-project/vllm-ascend/pull/4183) [#5303](https://github.com/vllm-project/vllm-ascend/pull/5303)
- **EPLB (Elastic Prefill Load Balancing)**: EPLB is now more stable with many bug fixes. Mix placement now works. [#6086](https://github.com/vllm-project/vllm-ascend/pull/6086)
- **EPLB (Elastic Prefill Load Balancing)**: [Experimental]EPLB is now more stable with many bug fixes. Mix placement now works. [#6086](https://github.com/vllm-project/vllm-ascend/pull/6086)
- **Full Decode Only Mode**: Added support for Qwen3-Next and DeepSeekv32 in full_decode_only mode with bug fixes. [#3949](https://github.com/vllm-project/vllm-ascend/pull/3949) [#3986](https://github.com/vllm-project/vllm-ascend/pull/3986) [#3763](https://github.com/vllm-project/vllm-ascend/pull/3763)
- **Model Runner V2**: Added basic support for Model Runner V2, the next generation of vLLM. It will be used by default in future releases. [#5210](https://github.com/vllm-project/vllm-ascend/pull/5210)
- **Model Runner V2**: [Experimental]Added basic support for Model Runner V2, the next generation of vLLM. It will be used by default in future releases. [#5210](https://github.com/vllm-project/vllm-ascend/pull/5210)

### Features

- **W8A16 Quantization**: Added new W8A16 quantization method support. [#4541](https://github.com/vllm-project/vllm-ascend/pull/4541)
- **UCM Connector**: Added UCMConnector for KV Cache Offloading. [#4411](https://github.com/vllm-project/vllm-ascend/pull/4411)
- **Batch Invariant**: Implemented basic framework for batch invariant feature. [#5517](https://github.com/vllm-project/vllm-ascend/pull/5517)
- **W8A16 Quantization**: [Experimental]Added new W8A16 quantization method support. [#4541](https://github.com/vllm-project/vllm-ascend/pull/4541)
- **UCM Connector**: [Experimental]Added UCMConnector for KV Cache Offloading. [#4411](https://github.com/vllm-project/vllm-ascend/pull/4411)
- **Batch Invariant**: [Experimental]Implemented basic framework for batch invariant feature. [#5517](https://github.com/vllm-project/vllm-ascend/pull/5517)
- **Sampling**: Enhanced sampling with async_scheduler and disable_padded_drafter_batch support in Eagle. [#4893](https://github.com/vllm-project/vllm-ascend/pull/4893)

### Hardware and Operator Support
Expand All @@ -51,13 +51,13 @@ This is the final release of v0.13.0 for vLLM Ascend. Please follow the [officia

Many custom ops and triton kernels were added in this release to speed up model performance:

- **DeepSeek Performance**: Improved performance for DeepSeek V3.2 by eliminating HD synchronization in async scheduling and optimizing memory usage for MTP. [#4805](https://github.com/vllm-project/vllm-ascend/pull/4805) [#2713](https://github.com/vllm-project/vllm-ascend/pull/2713)
- **Qwen3-Next Performance**: Improved performance with Triton ops and optimizations. [#5664](https://github.com/vllm-project/vllm-ascend/pull/5664) [#5984](https://github.com/vllm-project/vllm-ascend/pull/5984) [#5765](https://github.com/vllm-project/vllm-ascend/pull/5765)
- **DeepSeek Performance**: [Experimental]Improved performance for DeepSeek V3.2 by eliminating HD synchronization in async scheduling and optimizing memory usage for MTP. [#4805](https://github.com/vllm-project/vllm-ascend/pull/4805) [#2713](https://github.com/vllm-project/vllm-ascend/pull/2713)
- **Qwen3-Next Performance**: [Experimental]Improved performance with Triton ops and optimizations. [#5664](https://github.com/vllm-project/vllm-ascend/pull/5664) [#5984](https://github.com/vllm-project/vllm-ascend/pull/5984) [#5765](https://github.com/vllm-project/vllm-ascend/pull/5765)
- **FlashComm**: Enhanced FlashComm v2 optimization with o_shared linear and communication domain fixes. [#3232](https://github.com/vllm-project/vllm-ascend/pull/3232) [#4188](https://github.com/vllm-project/vllm-ascend/pull/4188) [#4458](https://github.com/vllm-project/vllm-ascend/pull/4458) [#5848](https://github.com/vllm-project/vllm-ascend/pull/5848)
- **MoE Optimization**: Optimized all2allv for MoE models and enhanced all-reduce skipping logic. [#3738](https://github.com/vllm-project/vllm-ascend/pull/3738) [#5329](https://github.com/vllm-project/vllm-ascend/pull/5329)
- **Attention Optimization**: Moved attention update stream out of loop, converted BSND to TND format for long sequence optimization, and removed transpose step after attention switching to transpose_batchmatmul. [#3848](https://github.com/vllm-project/vllm-ascend/pull/3848) [#3778](https://github.com/vllm-project/vllm-ascend/pull/3778) [#5390](https://github.com/vllm-project/vllm-ascend/pull/5390)
- **Quantization Performance**: Moved quantization before allgather in Allgather EP. [#3420](https://github.com/vllm-project/vllm-ascend/pull/3420)
- **Layerwise Connector**: Improved performance of Layerwise Connector. [#5303](https://github.com/vllm-project/vllm-ascend/pull/5303)
- **Layerwise Connector**: [Experimental]Improved performance of Layerwise Connector. [#5303](https://github.com/vllm-project/vllm-ascend/pull/5303)
- **Prefix Cache**: Improved performance of prefix cache features. [#4022](https://github.com/vllm-project/vllm-ascend/pull/4022)
- **Async Scheduling**: Fixed async copy and eliminated hangs in async scheduling. [#4113](https://github.com/vllm-project/vllm-ascend/pull/4113) [#4233](https://github.com/vllm-project/vllm-ascend/pull/4233)
- **Memory Operations**: Removed redundant D2H operations and deleted redundant operations in model_runner. [#4063](https://github.com/vllm-project/vllm-ascend/pull/4063) [#3677](https://github.com/vllm-project/vllm-ascend/pull/3677)
Expand Down
42 changes: 21 additions & 21 deletions docs/source/user_guide/support_matrix/supported_features.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,27 +8,27 @@ You can check the [support status of vLLM V1 Engine][v1_user_guide]. Below is th

| Feature | Status | Next Step |
|-------------------------------|----------------|------------------------------------------------------------------------|
| Chunked Prefill | 🟢 Functional | Functional, see detailed note: [Chunked Prefill][cp] |
| Automatic Prefix Caching | 🟢 Functional | Functional, see detailed note: [vllm-ascend#732][apc] |
| LoRA | 🟢 Functional | Functional, see detailed note: [LoRA][LoRA] |
| Speculative decoding | 🟢 Functional | Basic support |
| Pooling | 🟢 Functional | CI needed to adapt to more models; V1 support relies on vLLM support. |
| Enc-dec | 🟡 Planned | vLLM should support this feature first. |
| Multi Modality | 🟢 Functional | [Multi Modality][multimodal], optimizing and adapting more models |
| LogProbs | 🟢 Functional | CI needed |
| Prompt logProbs | 🟢 Functional | CI needed |
| Async output | 🟢 Functional | CI needed |
| Beam search | 🟢 Functional | CI needed |
| Guided Decoding | 🟢 Functional | [vllm-ascend#177][guided_decoding] |
| Tensor Parallel | 🟢 Functional | Make TP >4 work with graph mode. |
| Pipeline Parallel | 🟢 Functional | Write official guide and tutorial. |
| Expert Parallel | 🟢 Functional | Support dynamic EPLB. |
| Data Parallel | 🟢 Functional | Data Parallel support for Qwen3 MoE. |
| Prefill Decode Disaggregation | 🟢 Functional | Functional, xPyD is supported. |
| Quantization | 🟢 Functional | W8A8 available; working on more quantization method support (W4A8, etc) |
| Graph Mode | 🟢 Functional | Functional, see detailed note: [Graph Mode][graph_mode] |
| Sleep Mode | 🟢 Functional | Functional, see detailed note: [Sleep Mode][sleep_mode] |
| Context Parallel | 🟢 Functional | Functional, see detailed note: [Context Parallel][context_parallel] |
| Chunked Prefill | 🟢 Functional | Functional, see detailed note: [Chunked Prefill][cp] |
| Automatic Prefix Caching | 🟢 Functional | Functional, see detailed note: [vllm-ascend#732][apc] |
| LoRA | 🔵 Experimental | Functional, see detailed note: [LoRA][LoRA] |
| Speculative decoding | 🟢 Functional | Basic support |
| Pooling | 🔵 Experimental | CI needed to adapt to more models; V1 support relies on vLLM support. |
| Enc-dec | 🟡 Planned | vLLM should support this feature first. |
| Multi Modality | 🟢 Functional | [Multi Modality][multimodal], optimizing and adapting more models |
| LogProbs | 🟢 Functional | CI needed |
| Prompt logProbs | 🟢 Functional | CI needed |
| Async output | 🟢 Functional | CI needed |
| Beam search | 🔵 Experimental | CI needed |
| Guided Decoding | 🟢 Functional | [vllm-ascend#177][guided_decoding] |
| Tensor Parallel | 🟢 Functional | Make TP >4 work with graph mode. |
| Pipeline Parallel | 🟢 Functional | Write official guide and tutorial. |
| Expert Parallel | 🟢 Functional | Support dynamic EPLB. |
| Data Parallel | 🟢 Functional | Data Parallel support for Qwen3 MoE. |
| Prefill Decode Disaggregation | 🟢 Functional | Functional, xPyD is supported. |
| Quantization | 🟢 Functional | W8A8 available; working on more quantization method support (W4A8, etc) |
| Graph Mode | 🟢 Functional | Functional, see detailed note: [Graph Mode][graph_mode] |
| Sleep Mode | 🟢 Functional | Functional, see detailed note: [Sleep Mode][sleep_mode] |
| Context Parallel | 🟢 Functional | Functional, see detailed note: [Context Parallel][context_parallel] |

- 🟢 Functional: Fully operational, with ongoing optimizations.
- 🔵 Experimental: Experimental support, interfaces and functions may change.
Expand Down
Loading
Loading