EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Files
d781902ce9dbda8ab1e11bb0f2f0c1bc508fee7a
xc-llm-ascend/docs/source/user_guide/feature_guide/index.md
Marck 17da96658f [ModelLoader][Feature] Add rfork support for fast model loading (#7392) 
### What this PR does / why we need it?
Support an new load format: RFORK

For implementation details of this feature, please refer to #7441


### Does this PR introduce _any_ user-facing change?

add an new options for load-format: rfork

e.g.
```bash
vllm serve /workspace/models/Qwen3-8B --load-format rfork
```

### How was this patch tested?

- vLLM version: v0.17.0
- vLLM main:
4034c3d32e

Signed-off-by: Marck <1412354149@qq.com>
2026-03-25 16:40:30 +08:00

515 B
Raw Blame History

Feature Guide

This section provides a detailed usage guide of vLLM Ascend features.

:::{toctree} :caption: Feature Guide :maxdepth: 1 graph_mode cpu_binding quantization sleep_mode structured_output lora eplb_swift_balancer netloader rfork Multi_Token_Prediction dynamic_batch epd_disaggregation kv_pool external_dp large_scale_ep ucm_deployment Fine_grained_TP layer_sharding speculative_decoding context_parallel npugraph_ex weight_prefetch sequence_parallelism batch_invariance lmcache_ascend_deployment :::