docs: add Qwen/Qwen2.5-1.5B-Instruct to supported models

[LindseyMei]

Summary

Add Qwen/Qwen2.5-1.5B-Instruct to the list of tested models for the MetaX (MACA) backend in docs/models/supported_models.md.

Qwen2.5 uses the Qwen2ForCausalLM architecture, which is already supported on MetaX. This PR records a concrete, end-to-end validated model ID under that row (the Example HF Models column previously listed only Qwen2 / QwQ IDs).

Changes

• docs/models/supported_models.md: add Qwen/Qwen2.5-1.5B-Instruct to the Qwen2ForCausalLM example list, and note the Qwen2.5 family in the models column.

Validation

Offline generation was run on a single MetaX C500 and produced correct, coherent output.

Environment

Component	Version
GPU	MetaX C500 64GB
MACA	3.3.0.15 (KMD 3.8.30)
torch	2.8.0+metax3.3.0.2
vLLM (upstream, releases/v0.13.0, empty device)	0.13.1.dev0
vllm-metax plugin	0.13.0
mcoplib	0.3.1+maca3.3.0.15.torch2.8

Result

Engine initialized on the MACA FLASH_ATTN backend and produced 3/3 completions:

Prompt: 'The capital of France is'
Output: ' Paris. The capital of France is also the capital of which country? ...'

Prompt: 'Explain quantum computing in one sentence.'
Output: ' Quantum computing is a type of computing that uses quantum-mechanical phenomena, such as superposition and entanglement, to perform operations on data.'

Prompt: 'Write a short Python function that reverses a string.'
Output: ' ... def reverse_string(s: str) -> str: ...'

Test Plan

# MACA env + precompiled mcoplib kernels + HF mirror
export USE_PRECOMPILED_KERNEL=1
python validate_qwen2_5_1_5b.py

Expected: engine initializes with the metax platform activated and prints three coherent completions ending in VALIDATION OK.

[gemini-code-assist]

Code Review

This pull request updates the documentation in docs/models/supported_models.md to include Qwen2.5 and Qwen/Qwen2.5-1.5B-Instruct under the supported Qwen2ForCausalLM models. There are no review comments, and I have no feedback to provide.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.