A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 8, 06:15 UTC
[Doc] Add Mistral-7b-v0.3 model to the batch invariance validated model (#34584)
Signed-off-by: Parth Bansal <parthbansal127@gmail.com>
Parth Bansal committed
Feb 16, 2026 at 05:09 UTC
56530210944675b6adde20dae1ba6d224f68baf2
1 file changed
+1
docs/features/batch_invariance.md
+1
@@ -109,6 +109,7 @@ Batch invariance has been tested and verified on the following models:
109
- **Qwen2.5**: `Qwen/Qwen2.5-0.5B-Instruct`, `Qwen/Qwen2.5-1.5B-Instruct`, `Qwen/Qwen2.5-3B-Instruct`, `Qwen/Qwen2.5-7B-Instruct`, `Qwen/Qwen2.5-14B-Instruct`, `Qwen/Qwen2.5-32B-Instruct`
110
- **Llama 3**: `meta-llama/Llama-3.1-8B-Instruct`, `meta-llama/Llama-3.2-1B-Instruct`
111
- **GPT-OSS**: `openai/gpt-oss-20b`, `openai/gpt-oss-120b`
112
+- **Mistral**: `mistralai/Mistral-7B-v0.3`
113
114
Other models may also work, but these have been explicitly validated. If you encounter issues with a specific model, please report them on the [GitHub issue tracker](https://github.com/vllm-project/vllm/issues/new/choose).
115