anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Feat] Add NPU Backend support for vLLM-Omni (#89)

Browse Source 
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
This commit is contained in:
Canlin Guo authored and GitHub committed 2025-11-30 20:39:06 +08:00
1 parent 88c00fb271
commit ec9e04027d
25 files changed
+2932 -85
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/api/README.md
+5
View File
@@ -111,3 +111,8 @@ Worker classes and model runners for distributed inference.
- [vllm_omni.worker.gpu_generation_model_runner.GPUGenerationModelRunner][]
- [vllm_omni.worker.gpu_generation_worker.GPUGenerationWorker][]
- [vllm_omni.worker.gpu_model_runner.OmniGPUModelRunner][]
- [vllm_omni.worker.npu.npu_ar_model_runner.NPUARModelRunner][]
- [vllm_omni.worker.npu.npu_ar_worker.NPUARWorker][]
- [vllm_omni.worker.npu.npu_diffusion_model_runner.NPUDiffusionModelRunner][]
- [vllm_omni.worker.npu.npu_diffusion_worker.NPUDiffusionWorker][]
- [vllm_omni.worker.npu.npu_model_runner.OmniNPUModelRunner][]