571f88f85e
1. Update 0.9.0rc1 release date 2. Update feature and model support list 3. Add DP known issue to release note Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
5.0 KiB
5.0 KiB
Feature Support
The feature support principle of vLLM Ascend is: aligned with the vLLM. We are also actively collaborating with the community to accelerate support.
You can check the support status of vLLM V1 Engine. Below is the feature support status of vLLM Ascend:
| Feature | vLLM V0 Engine | vLLM V1 Engine | Next Step |
|---|---|---|---|
| Chunked Prefill | 🟢 Functional | 🟢 Functional | Functional, see detail note: Chunked Prefill |
| Automatic Prefix Caching | 🟢 Functional | 🟢 Functional | Functional, see detail note: vllm-ascend#732 |
| LoRA | 🟢 Functional | 🟢 Functional | vllm-ascend#396, vllm-ascend#893 |
| Prompt adapter | 🔴 No plan | 🔴 No plan | This feature has been deprecated by vllm. |
| Speculative decoding | 🟢 Functional | 🟢 Functional | Basic support |
| Pooling | 🟢 Functional | 🟡 Planned | CI needed and adapting more models; V1 support rely on vLLM support. |
| Enc-dec | 🔴 NO plan | 🟡 Planned | Plan in 2025.06.30 |
| Multi Modality | 🟢 Functional | 🟢 Functional | Tutorial, optimizing and adapting more models |
| LogProbs | 🟢 Functional | 🟢 Functional | CI needed |
| Prompt logProbs | 🟢 Functional | 🟢 Functional | CI needed |
| Async output | 🟢 Functional | 🟢 Functional | CI needed |
| Multi step scheduler | 🟢 Functional | 🔴 Deprecated | vllm#8779, replaced by vLLM V1 Scheduler |
| Best of | 🟢 Functional | 🔴 Deprecated | vllm#13361, CI needed |
| Beam search | 🟢 Functional | 🟢 Functional | CI needed |
| Guided Decoding | 🟢 Functional | 🟢 Functional | vllm-ascend#177 |
| Tensor Parallel | 🟢 Functional | 🟢 Functional | CI needed |
| Pipeline Parallel | 🟢 Functional | 🟢 Functional | CI needed |
| Expert Parallel | 🔴 NO plan | 🟢 Functional | CI needed; No plan on V0 support |
| Data Parallel | 🔴 NO plan | 🟢 Functional | CI needed; No plan on V0 support |
| Prefill Decode Disaggregation | 🟢 Functional | 🟢 Functional | 1P1D available, working on xPyD and V1 support. |
| Quantization | 🟢 Functional | 🟢 Functional | W8A8 available, CI needed; working on more quantization method support |
| Graph Mode | 🔴 NO plan | 🔵 Experimental | Experimental, see detail note: vllm-ascend#767 |
| Sleep Mode | 🟢 Functional | 🟢 Functional | level=1 available, CI needed, working on V1 support |
- 🟢 Functional: Fully operational, with ongoing optimizations.
- 🔵 Experimental: Experimental support, interfaces and functions may change.
- 🚧 WIP: Under active development, will be supported soon.
- 🟡 Planned: Scheduled for future implementation (some may have open PRs/RFCs).
- 🔴 NO plan / Deprecated: No plan for V0 or deprecated by vLLM v1.