deepseek-ai/DeepSeek-V2-Lite

Explore deepseek-ai/DeepSeek-V2-Lite: model specifications, capabilities, benchmark results, platform pricing and original sources.

vertexAI/publishers/hf-deepseek-ai/models/deepseek-v2-lite@001

Specifications & capabilities

Input
text
Output
text
Published model ID
DeepSeek-V2-Lite

Evaluations

1–20 / 327

LLM-Perf

4,043,245.108

source id
llmPerf
leaderboard name
prefill efficiency value
dimension
runtime
metric
prefill efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cpu
config.backend.library
transformers
config.backend.version
2.5.0+cpu
config.environment.cpu
Intel(R) Xeon(R) Platinum 8488C
config.backend.eval_mode
True
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
96
config.environment.processor
x86_64
config.environment.cpu_ram_mb
199386.689536
config.backend.autocast_enabled
False
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.23.2
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.0.1
config.environment.transformers_version
4.45.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
prefill efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
af6a52d37382cfbc4542581cebc1e916a595b651708e0a5d8217d99ec30b4830
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

3,846,411.777

source id
llmPerf
leaderboard name
prefill efficiency value
dimension
runtime
metric
prefill efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cpu
config.backend.library
transformers
config.backend.version
2.5.0+cpu
config.environment.cpu
Intel(R) Xeon(R) Platinum 8488C
config.backend.eval_mode
True
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
96
config.environment.processor
x86_64
config.environment.cpu_ram_mb
199386.689536
config.backend.autocast_enabled
False
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.23.2
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.0.1
config.environment.transformers_version
4.45.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
prefill efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
a236e83bf2f29de32f4ba4a3f8095b2a47a8304ff09a000403f768b53d2b9892
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

274,228.766

source id
llmPerf
leaderboard name
decode efficiency value
dimension
runtime
metric
decode efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_4bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
decode efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
95c6ca2c7bd4d48e34508039093b8e8282f3449e253674eda8ddca51441a01b3
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

263,500.936

source id
llmPerf
leaderboard name
decode efficiency value
dimension
runtime
metric
decode efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
flash_attention_2
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_4bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
decode efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
da975ca28a2daa84d7bbf477a5ba389ba1bfb2f9fdec8b1801b91494c0bd7529
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

250,515.23

source id
llmPerf
leaderboard name
decode efficiency value
dimension
runtime
metric
decode efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cpu
config.backend.library
transformers
config.backend.version
2.5.0+cpu
config.environment.cpu
Intel(R) Xeon(R) Platinum 8488C
config.backend.eval_mode
True
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
bfloat16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
96
config.environment.processor
x86_64
config.environment.cpu_ram_mb
199386.689536
config.backend.autocast_enabled
False
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.23.2
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.0.1
config.environment.transformers_version
4.45.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
decode efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
af6a52d37382cfbc4542581cebc1e916a595b651708e0a5d8217d99ec30b4830
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

217,177.753

source id
llmPerf
leaderboard name
decode efficiency value
dimension
runtime
metric
decode efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xT4.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
config.environment.gpu
['Tesla T4']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
8
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
33163.747328
config.environment.gpu_vram_mb
16106127360
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_4bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
decode efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xT4.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
609738beeb029454ed62f7cbee993c6c707fb7365b4e0f8c3ed234484e58c01e
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

216,976.835

source id
llmPerf
leaderboard name
decode efficiency value
dimension
runtime
metric
decode efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cpu
config.backend.library
transformers
config.backend.version
2.5.0+cpu
config.environment.cpu
Intel(R) Xeon(R) Platinum 8488C
config.backend.eval_mode
True
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
96
config.environment.processor
x86_64
config.environment.cpu_ram_mb
199386.689536
config.backend.autocast_enabled
False
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.environment.optimum_version
1.23.2
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.0.1
config.environment.transformers_version
4.45.2
config.scenario.input_shapes.batch_size
1
config.scenario.input_shapes.num_choices
2
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
metric_kind
decode efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cpu-unquantized-32vCPU-C7i.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
a236e83bf2f29de32f4ba4a3f8095b2a47a8304ff09a000403f768b53d2b9892
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

200,098.008

source id
llmPerf
leaderboard name
decode efficiency value
dimension
runtime
metric
decode efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
flash_attention_2
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
decode efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
5470a67f9fb4f0e209c9b3fe2ec0403653f7449ffadb248606901cbe0357145b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

193,730.739

source id
llmPerf
leaderboard name
decode efficiency value
dimension
runtime
metric
decode efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
decode efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
01a25c43c7a4098542aefb57863175d567093ed6ba99733db89382038c32276b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

166,544.438

source id
llmPerf
leaderboard name
prefill efficiency value
dimension
runtime
metric
prefill efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
flash_attention_2
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
prefill efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
5470a67f9fb4f0e209c9b3fe2ec0403653f7449ffadb248606901cbe0357145b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

165,219.139

source id
llmPerf
leaderboard name
prefill efficiency value
dimension
runtime
metric
prefill efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
prefill efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
01a25c43c7a4098542aefb57863175d567093ed6ba99733db89382038c32276b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

84,176.341

source id
llmPerf
leaderboard name
prefill efficiency value
dimension
runtime
metric
prefill efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_4bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
prefill efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
95c6ca2c7bd4d48e34508039093b8e8282f3449e253674eda8ddca51441a01b3
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

83,794.282

source id
llmPerf
leaderboard name
prefill efficiency value
dimension
runtime
metric
prefill efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
flash_attention_2
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_4bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
prefill efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
da975ca28a2daa84d7bbf477a5ba389ba1bfb2f9fdec8b1801b91494c0bd7529
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

50,450.299

source id
llmPerf
leaderboard name
prefill efficiency value
dimension
runtime
metric
prefill efficiency value
rank
1
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xT4.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz
config.environment.gpu
['Tesla T4']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
8
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
33163.747328
config.environment.gpu_vram_mb
16106127360
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_4bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
prefill efficiency value
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xT4.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
609738beeb029454ed62f7cbee993c6c707fb7365b4e0f8c3ed234484e58c01e
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

36,979.831

source id
llmPerf
leaderboard name
prefill memory max_ram
dimension
runtime
metric
prefill memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
flash_attention_2
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
prefill memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
5470a67f9fb4f0e209c9b3fe2ec0403653f7449ffadb248606901cbe0357145b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

36,979.831

source id
llmPerf
leaderboard name
decode memory max_ram
dimension
runtime
metric
decode memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
flash_attention_2
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
decode memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
5470a67f9fb4f0e209c9b3fe2ec0403653f7449ffadb248606901cbe0357145b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

36,896.113

source id
llmPerf
leaderboard name
load_model memory max_ram
dimension
runtime
metric
load_model memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
flash_attention_2
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
load_model memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
5470a67f9fb4f0e209c9b3fe2ec0403653f7449ffadb248606901cbe0357145b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

36,890.747

source id
llmPerf
leaderboard name
prefill memory max_ram
dimension
runtime
metric
prefill memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
prefill memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
01a25c43c7a4098542aefb57863175d567093ed6ba99733db89382038c32276b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

36,890.747

source id
llmPerf
leaderboard name
decode memory max_ram
dimension
runtime
metric
decode memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
decode memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
01a25c43c7a4098542aefb57863175d567093ed6ba99733db89382038c32276b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

LLM-Perf

36,812.169

source id
llmPerf
leaderboard name
load_model memory max_ram
dimension
runtime
metric
load_model memory max_ram
rank
1
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
execution
config.backend.name
pytorch
config.backend.seed
42
config.backend.task
text-generation
config.backend.device
cuda
config.backend.library
transformers
config.backend.version
2.5.1+cu124
config.environment.cpu
AMD EPYC 7R32
config.environment.gpu
['NVIDIA A10G']
config.backend.eval_mode
True
config.backend.device_ids
0
config.backend.model_type
deepseek_v2
config.backend.no_weights
True
config.environment.system
Linux
config.backend.torch_dtype
float16
config.environment.machine
x86_64
config.backend.torch_compile
False
config.environment.cpu_count
16
config.environment.gpu_count
1
config.environment.processor
x86_64
config.environment.cpu_ram_mb
66697.248768
config.environment.gpu_vram_mb
24146608128
config.backend.autocast_enabled
False
config.environment.peft_version
0.14.0
config.environment.python_version
3.10.12
config.backend.attn_implementation
eager
config.backend.deepspeed_inference
False
config.backend.quantization_scheme
bnb
config.environment.optimum_version
1.23.3
config.backend.to_bettertransformer
False
config.backend.torch_compile_target
forward
config.environment.accelerate_version
1.2.0
config.environment.transformers_version
4.47.0
config.scenario.input_shapes.batch_size
1
config.environment.optimum_benchmark_version
0.5.0.dev0
config.scenario.input_shapes.sequence_length
256
config.backend.model_kwargs.trust_remote_code
True
config.scenario.generate_kwargs.max_new_tokens
64
config.scenario.generate_kwargs.min_new_tokens
64
config.backend.quantization_config.load_in_8bit
True
config.backend.quantization_config.llm_int8_threshold
0.0
metric_kind
load_model memory max_ram
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
optimum-benchmark/llm-perf-leaderboard/perf-df-pytorch-cuda-bnb-1xA10.csv
published_at
2024-12-13T10:07:03Z
source_revision
2fa8d8c300c4eb6e744d5e35999db926c0c26e90e767e4c38da326eebe21a92b
metric_population
1
benchmark_evaluation
true
comparison_configuration_sha256
01a25c43c7a4098542aefb57863175d567093ed6ba99733db89382038c32276b
complete_configuration_location
source record config and original CSV artifact
source model id
deepseek-ai/DeepSeek-V2-Lite
Original result ↗

Provider specifications & access

1–1 / 1

deepseek-ai/DeepSeek-V2-Lite ↗

source model id
publishers/hf-deepseek-ai/models/deepseek-v2-lite@001
hosting
vertex-self-deployed
platforms
  • Google Cloud Vertex AI
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    32 / 100

    source id
    stanfordFMTI
    canonical model id
    vertexAI/publishers/hf-deepseek-ai/models/deepseek-v2-lite@001
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    DeepSeek
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    32 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Original sources

    1–6 / 6

    Hugging Face · deepseek-ai/DeepSeek-V2-Lite ↗

    Google Cloud · Model page ↗

    Google Cloud · Model documentation ↗

    GitHub · Catalog ↗

    Google Cloud · Catalog ↗

    Hugging Face · Catalog ↗

    Source links

    1–3 / 3

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace