Support DeepSeekV3-style block FP8 quantization

[mgoin]

Quite a few things packed into one here, but the goal is to support the 128x128 weight and 1x128 input quantization adopted by deepseekv3 and qwen3 models. See examples: https://huggingface.co/deepseek-ai/DeepSeek-V3 and https://huggingface.co/Qwen/Qwen3-0.6B-FP8

• Added BLOCK static quantization paths for weight quantization.
• Added GROUP dynamic quantization paths for per-token-group input quantization. I feel like this is more understandable than the "1x128" block input quantization deepseek uses.
• I’ve updated all of the places where block_structure was previously treated as an “NxM” string so that it now uses a Python list of two integers (e.g. [128, 128]). I added a pydantic validator that can convert this automatically for old checkpoints that use the string.

Here is the scheme I am proposing to support this:

# Block‐wise FP8 (deepseekv3-style quantization):
# static 128x128 per‐block weights and 
# dynamic per‐token‐group activations
FP8_BLOCK = dict(
    weights=QuantizationArgs(
        num_bits=8,
        type=QuantizationType.FLOAT,
        strategy=QuantizationStrategy.BLOCK,
        symmetric=True,
        dynamic=False,
        block_structure=[128, 128],
    ),
    input_activations=QuantizationArgs(
        num_bits=8,
        type=QuantizationType.FLOAT,
        strategy=QuantizationStrategy.GROUP,
        symmetric=True,
        dynamic=True,
        observer=None,
        group_size=128,
    ),
)

Added this model to hugging face: nm-testing/Qwen3-0.6B-FP8-BLOCK

[dsikka]

Can you produce a test model to nm-testing andd it to this PR?

[kylesayrs]

Looks good!

[brian-dellabetta]

awesome work! clear with nice tests