|
1 |
| -20240613174456, tok/s= 31.00, mem/s= 819.31 GB/s, peak_mem=27.23 GB, model_size=26.43 GB quant: None, mod: Llama-2-7b-chat-hf, compile: False, compile_prefill: False, dtype: torch.float32, device: cuda repro: python generate.py --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.float32 --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
2 |
| -20240613174647, tok/s= 27.37, mem/s= 361.70 GB/s, peak_mem=13.62 GB, model_size=13.21 GB quant: None, mod: Llama-2-7b-chat-hf, compile: False, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
3 |
| -20240613182718, tok/s=106.44, mem/s=1406.56 GB/s, peak_mem=13.88 GB, model_size=13.21 GB quant: None, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: True, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --compile_prefill --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
4 |
| -20240613174842, tok/s=105.13, mem/s=1389.20 GB/s, peak_mem=13.88 GB, model_size=13.21 GB quant: None, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
5 |
| -20240613183515, tok/s= 9.13, mem/s= 60.44 GB/s, peak_mem= 8.33 GB, model_size= 6.62 GB quant: int8dq, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8dq --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
6 |
| -20240613183057, tok/s=149.30, mem/s= 988.60 GB/s, peak_mem= 8.95 GB, model_size= 6.62 GB quant: int8wo, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8wo --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
7 |
| -20240613182903, tok/s=200.52, mem/s= 749.11 GB/s, peak_mem= 4.50 GB, model_size= 3.74 GB quant: int4wo-64, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int4wo-64 --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
8 |
| -20240613191947, tok/s=158.20, mem/s=1063.00 GB/s, peak_mem= 8.89 GB, model_size= 6.72 GB quant: autoquant, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: True, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization autoquant --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --compile_prefill --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
9 |
| -20240613165002, tok/s= 28.99, mem/s= 870.30 GB/s, peak_mem=32.34 GB, model_size=30.02 GB quant: None, mod: Meta-Llama-3-8B, compile: False, compile_prefill: False, dtype: torch.float32, device: cuda repro: python generate.py --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.float32 --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
10 |
| -20240613165204, tok/s= 26.63, mem/s= 399.74 GB/s, peak_mem=16.16 GB, model_size=15.01 GB quant: None, mod: Meta-Llama-3-8B, compile: False, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
11 |
| -20240613173355, tok/s= 96.00, mem/s=1440.96 GB/s, peak_mem=16.43 GB, model_size=15.01 GB quant: None, mod: Meta-Llama-3-8B, compile: True, compile_prefill: True, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --compile_prefill --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
12 |
| -20240613165407, tok/s= 94.99, mem/s=1425.76 GB/s, peak_mem=16.43 GB, model_size=15.01 GB quant: None, mod: Meta-Llama-3-8B, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
13 |
| -20240613174305, tok/s= 8.35, mem/s= 62.80 GB/s, peak_mem= 8.98 GB, model_size= 7.52 GB quant: int8dq, mod: Meta-Llama-3-8B, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8dq --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
14 |
| -20240613173835, tok/s=138.99, mem/s=1045.23 GB/s, peak_mem=10.42 GB, model_size= 7.52 GB quant: int8wo, mod: Meta-Llama-3-8B, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8wo --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
15 |
| -20240613173609, tok/s=178.52, mem/s= 753.69 GB/s, peak_mem= 6.62 GB, model_size= 4.22 GB quant: int4wo-64, mod: Meta-Llama-3-8B, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int4wo-64 --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
16 |
| -20240613200137, tok/s=141.06, mem/s=1062.97 GB/s, peak_mem=10.03 GB, model_size= 7.54 GB quant: autoquant, mod: Meta-Llama-3-8B, compile: True, compile_prefill: True, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization autoquant --checkpoint_path ../../../../gpt-fast/checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --compile_prefill --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 1 | +20240619101342, tok/s= 29.85, mem/s= 788.87 GB/s, peak_mem=27.23 GB, model_size=26.43 GB quant: None, mod: Llama-2-7b-chat-hf, compile: False, compile_prefill: False, dtype: torch.float32, device: cuda repro: python generate.py --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.float32 --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 2 | +20240619101537, tok/s= 26.38, mem/s= 348.57 GB/s, peak_mem=13.62 GB, model_size=13.21 GB quant: None, mod: Llama-2-7b-chat-hf, compile: False, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 3 | +20240619105331, tok/s=106.55, mem/s=1408.06 GB/s, peak_mem=13.88 GB, model_size=13.21 GB quant: None, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: True, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --compile_prefill --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 4 | + |
| 5 | +20240619105522, tok/s=105.14, mem/s=1389.35 GB/s, peak_mem=13.88 GB, model_size=13.21 GB quant: None, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 6 | +20240619105921, tok/s= 9.20, mem/s= 60.93 GB/s, peak_mem= 8.33 GB, model_size= 6.62 GB quant: int8dq, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8dq --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 7 | +20240619110107, tok/s=150.18, mem/s= 994.40 GB/s, peak_mem= 8.95 GB, model_size= 6.62 GB quant: int8wo, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8wo --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 8 | +20240619110248, tok/s=199.86, mem/s= 746.66 GB/s, peak_mem= 4.50 GB, model_size= 3.74 GB quant: int4wo-64, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int4wo-64 --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 9 | +20240619114518, tok/s=159.22, mem/s=1069.87 GB/s, peak_mem= 8.91 GB, model_size= 6.72 GB quant: autoquant, mod: Llama-2-7b-chat-hf, compile: True, compile_prefill: True, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization autoquant --checkpoint_path ../../../checkpoints/meta-llama/Llama-2-7b-chat-hf/model.pth --device cuda --precision torch.bfloat16 --compile --compile_prefill --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 10 | + |
| 11 | +20240619114732, tok/s= 30.46, mem/s= 914.43 GB/s, peak_mem=32.34 GB, model_size=30.02 GB quant: None, mod: Meta-Llama-3-8B, compile: False, compile_prefill: False, dtype: torch.float32, device: cuda repro: python generate.py --checkpoint_path ../../../checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.float32 --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 12 | +20240619114939, tok/s= 26.56, mem/s= 398.65 GB/s, peak_mem=16.16 GB, model_size=15.01 GB quant: None, mod: Meta-Llama-3-8B, compile: False, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 13 | +20240619122811, tok/s= 96.09, mem/s=1442.32 GB/s, peak_mem=16.43 GB, model_size=15.01 GB quant: None, mod: Meta-Llama-3-8B, compile: True, compile_prefill: True, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --compile_prefill --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 14 | + |
| 15 | +20240619123018, tok/s= 94.97, mem/s=1425.55 GB/s, peak_mem=16.43 GB, model_size=15.01 GB quant: None, mod: Meta-Llama-3-8B, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --checkpoint_path ../../../checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 16 | +20240619123441, tok/s= 8.44, mem/s= 63.45 GB/s, peak_mem= 8.98 GB, model_size= 7.52 GB quant: int8dq, mod: Meta-Llama-3-8B, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8dq --checkpoint_path ../../../checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 17 | +20240619123652, tok/s=139.76, mem/s=1051.02 GB/s, peak_mem=10.42 GB, model_size= 7.52 GB quant: int8wo, mod: Meta-Llama-3-8B, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int8wo --checkpoint_path ../../../checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 18 | +20240619123847, tok/s=179.44, mem/s= 757.60 GB/s, peak_mem= 6.62 GB, model_size= 4.22 GB quant: int4wo-64, mod: Meta-Llama-3-8B, compile: True, compile_prefill: False, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization int4wo-64 --checkpoint_path ../../../checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
| 19 | +20240619131959, tok/s=137.71, mem/s=1037.74 GB/s, peak_mem=11.08 GB, model_size= 7.54 GB quant: autoquant, mod: Meta-Llama-3-8B, compile: True, compile_prefill: True, dtype: torch.bfloat16, device: cuda repro: python generate.py --quantization autoquant --checkpoint_path ../../../checkpoints/meta-llama/Meta-Llama-3-8B/model.pth --device cuda --precision torch.bfloat16 --compile --compile_prefill --num_samples 5 --max_new_tokens 200 --top_k 200 --temperature 0.8 |
0 commit comments