feat: Implement BURST and STEP load patterns

Problem

LoadPatternType.BURST and LoadPatternType.STEP are defined in the config schema enum but have no scheduler implementation:

# src/inference_endpoint/config/schema.py:72-73
BURST = "burst"
STEP = "step"

A user who selects either pattern in their YAML config will get no error, but also no expected behavior — the scheduler will silently fall through or raise an unhandled case.

Expected Behavior

• BURST: Issue a configurable burst of N queries at a fixed interval (e.g. N queries every T seconds)
• STEP: Incrementally step up QPS in stages (useful for finding saturation point)

Files to Modify

• src/inference_endpoint/config/schema.py — document the pattern parameters
• src/inference_endpoint/load_generator/scheduler.py — add scheduler implementations
• src/inference_endpoint/config/runtime_settings.py — ensure RuntimeSettings handles these patterns

Start with the LoadPatternType entries at src/inference_endpoint/config/schema.py:72-73, then inspect src/inference_endpoint/load_generator/scheduler.py and src/inference_endpoint/config/runtime_settings.py to understand existing pattern handling and configuration conventions. Done means BURST and STEP configurations are accepted and produce the documented query schedules, with coverage for both patterns and their parameters.