xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-26 21:34:39 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add CPU support model (#28697)

Browse Source 
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
This commit is contained in:
Louie Tsai 2025-11-18 23:47:57 -08:00 committed by GitHub
parent 7ed27f3cb5
commit ae4821a108
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 26 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
docs/models/hardware_supported_models/cpu.md Normal file
View File

@ -0,0 +1,26 @@
# CPU - Intel® Xeon®
## Supported Models
### Text-only Language Models
| Model | Architecture | Supported |
|--------------------------------------|-------------------------------------------|-----------|
| meta-llama/Llama-3.1 / 3.3 | LlamaForCausalLM | ✅ |
| meta-llama/Llama-4-Scout | Llama4ForConditionalGeneration | ✅ |
| meta-llama/Llama-4-Maverick | Llama4ForConditionalGeneration | ✅ |
| ibm-granite/granite (Granite-MOE) | GraniteMoeForCausalLM | ✅ |
| Qwen/Qwen3 | Qwen3ForCausalLM | ✅ |
| zai-org/GLM-4.5 | GLMForCausalLM | ✅ |
| google/gemma | GemmaForCausalLM | ✅ |
### Multimodal Language Models
| Model | Architecture | Supported |
|--------------------------------------|-------------------------------------------|-----------|
| Qwen/Qwen2.5-VL | Qwen2VLForConditionalGeneration | ✅ |
| openai/whisper | WhisperForConditionalGeneration | ✅ |
✅ Runs and optimized.
🟨 Runs and correct but not optimized to green yet.
❌ Does not pass accuracy test or does not run.