EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

[doc] fix feature support (#70)

Browse Source 
Check and update the feature support table.

- both multi-step and speculative decoding require adaptation of corresponding workers
- prompt adapter (finetune method) require adaption in worker.py and model_runner.py

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-02-17 15:43:37 +08:00
committed by GitHub
parent 36ea38fde5
commit c935b7006c
1 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
docs/source/features/suppoted_features.md
View File

@@ -3,17 +3,19 @@
| Feature | Supported | Note |
|---------|-----------|------|
| Chunked Prefill | ✗ | Plan in 2025 Q1 |
| Automatic Prefix Caching | ✅ | Improve performance in 2025 Q1 |
| Automatic Prefix Caching | ✅ | Improve performance in 2025 Q2 |
| LoRA | ✗ | Plan in 2025 Q1 |
| Prompt adapter | ✅ ||
| Speculative decoding | ✅ | Improve accuracy in 2025 Q1|
| Pooling | ✗ | Plan in 2025 Q1 |
| Enc-dec | ✗ | Plan in 2025 Q1 |
| Prompt adapter | ✗ | Plan in 2025 Q1 |
| Speculative decoding | ✗ | Plan in 2025 Q1 |
| Pooling | ✗ | Plan in 2025 Q2 |
| Enc-dec | ✗ | Plan in 2025 Q2 |
| Multi Modality | ✅ (LLaVA/Qwen2-vl/Qwen2-audio/internVL)| Add more model support in 2025 Q1 |
| LogProbs | ✅ ||
| Prompt logProbs | ✅ ||
| Async output | ✅ ||
| Multi step scheduler | ✅ ||
| Multi step scheduler | ✗ | Plan in 2025 Q1 |
| Best of | ✅ ||
| Beam search | ✅ ||
| Guided Decoding | ✗ | Plan in 2025 Q1 |
| Tensor Parallel | ✅ | Only "mp" supported now |
| Pipeline Parallel | ✅ | Only "mp" supported now |