Fixed the linux build and added numbers for raspberry PI based on cactus test on INT4 with the following numbers:

╔══════════════════════════════════════════╗
║ 1K CONTEXT TEST ║
╚══════════════════════════════════════════╝
Response: The given data represents the growth of the number of people in a country over different periods (represented by Data points) and times (represented by Time). Each time represents one year, starting from 1990 to -2024. In this data, we can observe that: * The growth rate seems to be increasing over time. * The initial value for 1990 is approximately 3.2% higher compared to other years, while in -2024 it's less than [-> stopped]

[Results]
"success": true,
"error": null,
"cloud_handoff": false,
"response": "The given data represents the growth of the number of people in a country over different periods (represented by Data points) and times (represented by Time). Each time represents one year, starting from 1990 to -2024.\n\nIn this data, we can observe that:\n\n* The growth rate seems to be increasing over time.\n* The initial value for 1990 is approximately 3.2% higher compared to other years, while in -2024 it's less than",
"function_calls": [],
"confidence": 0.8602,
"time_to_first_token_ms": 4423.79,
"total_time_ms": 8103.16,
"prefill_tps": 205.48,
"decode_tps": 26.91,
"ram_usage_mb": 373.16,
"prefill_tokens": 909,
"decode_tokens": 100,
"total_tokens": 1009
└─ Status: PASSED ✓
✓ PASS │ 1k_context

══════════════════════════════════════════════════════════════════════════════════════╗
║ Running VLM Tests ║
╚══════════════════════════════════════════════════════════════════════════════════════╝

╔══════════════════════════════════════════╗
║ VLM MULTI-TURN TEST ║
╚══════════════════════════════════════════╝

[Turn 1]
User: Describe what is happening in this image in two sentences.
Assistant: The image features a close-up of a light brown creature's face, head, and upper body. The subject appears to be calm and relaxed. The details are vivid with realistic facial features that capture the essence of life in this animal's life.

[Results - Turn 1]
"success": true,
"error": null,
"cloud_handoff": false,
"response": "The image features a close-up of a light brown creature's face, head, and upper body. The subject appears to be calm and relaxed. The details are vivid with realistic facial features that capture the essence of life in this animal's life.",
"function_calls": [],
"confidence": 0.8416,
"time_to_first_token_ms": 1845.47,
"total_time_ms": 3404.70,
"prefill_tps": 47.14,
"decode_tps": 30.78,
"ram_usage_mb": 657.25,
"prefill_tokens": 87,
"decode_tokens": 49,
"total_tokens": 136

[Turn 2]
User: Describe the image once again.
Assistant: The image presents an intimate portrait of an exotic creature, likely from the primate kingdom, whose distinct coloration suggests it may be a type of monkey or small primate. Its skin tone is predominantly light brown with dark brown accents accentuating certain areas, giving it a rich textured appearance. In terms of anatomy visible in the face: the eyes are expressive and prominent against the furrowed brow structure that suggests alertness or contemplation; one can note subtle variations in skin colors around these features that highlight differences among individual animals. The nose area is depicted prominently below where one would expect to locate ears due to its unique shape and size; there's a soft gray hue suggesting this may not be part of the primary ear area, which often has different coloration due to genetic variation or mutation; the skin under one's mouth shows some gradient tones transitioning from lighter at base to darker at tips. The eyes are large, oval-shaped with green undertones that might imply depth, although they are not as

[Results - Turn 2]
"success": false,
"error": null,
"cloud_handoff": true,
"response": "The image presents an intimate portrait of an exotic creature, likely from the primate kingdom, whose distinct coloration suggests it may be a type of monkey or small primate. Its skin tone is predominantly light brown with dark brown accents accentuating certain areas, giving it a rich textured appearance.\n\nIn terms of anatomy visible in the face: the eyes are expressive and prominent against the furrowed brow structure that suggests alertness or contemplation; one can note subtle variations in skin colors around these features that highlight differences among individual animals. The nose area is depicted prominently below where one would expect to locate ears due to its unique shape and size; there's a soft gray hue suggesting this may not be part of the primary ear area, which often has different coloration due to genetic variation or mutation; the skin under one's mouth shows some gradient tones transitioning from lighter at base to darker at tips.\n\nThe eyes are large, oval-shaped with green undertones that might imply depth, although they are not as prominent",
"function_calls": [],
"confidence": 0.8249,
"time_to_first_token_ms": 2209.86,
"total_time_ms": 9471.05,
"prefill_tps": 69.24,
"decode_tps": 28.65,
"ram_usage_mb": 702.12,
"prefill_tokens": 153,
"decode_tokens": 209,
"total_tokens": 362
✓ PASS │ vlm_multiturn
────────────────────────────────────────────────────────────────────────────────────────
✓ All 1 tests passed!

(venv) (base) karen@cactuspi:~/Documents/cactus $

╔══════════════════════════════════════════╗
║ TRANSCRIPTION ║
╚══════════════════════════════════════════╝
Transcript: Hello, hello, hello. Um, quickly testing out, creating a way to file through voice memos. Um, the goal is to use this way file to test out whisper. Hopefully this will transcribe properly. That's all I can hope for. All right. Here we go.

[Results]
"success": true,
"error": null,
"cloud_handoff": false,
"response": "Hello, hello, hello. Um, quickly testing out, creating a way to file through voice memos. Um, the goal is to use this way file to test out whisper. Hopefully this will transcribe properly. That's all I can hope for. All right. Here we go.",
"function_calls": [],
"confidence": 0.9807,
"time_to_first_token_ms": 1349.41,
"total_time_ms": 1868.13,
"prefill_tps": 0.00,
"decode_tps": 117.60,
"ram_usage_mb": 214.25,
"prefill_tokens": 0,
"decode_tokens": 62,
"total_tokens": 62
✓ PASS │ transcription