sharpenb commited on
Commit
4e86d60
1 Parent(s): 52ba849

13caa366ee9dac6a1f0966b3a160015e3d5d496e6832888a6d94de2f7c9b224c

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. plots.png +0 -0
  3. results.json +24 -24
  4. smash_config.json +5 -5
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/tmp/tmp6tqwsht_",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "/tmp/tmpoau7b4ew",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
plots.png CHANGED
results.json CHANGED
@@ -1,30 +1,30 @@
1
  {
2
  "base_current_gpu_type": "NVIDIA A100-PCIE-40GB",
3
  "base_current_gpu_total_memory": 40339.3125,
4
- "base_token_generation_latency_sync": 76.91910247802734,
5
- "base_token_generation_latency_async": 76.82386375963688,
6
- "base_token_generation_throughput_sync": 0.013000671715919452,
7
- "base_token_generation_throughput_async": 0.013016788678173697,
8
- "base_token_generation_CO2_emissions": 3.9930267542867864e-05,
9
- "base_token_generation_energy_consumption": 0.013695786831045186,
10
- "base_inference_latency_sync": 75.31489334106445,
11
- "base_inference_latency_async": 74.6358871459961,
12
- "base_inference_throughput_sync": 0.013277586352960592,
13
- "base_inference_throughput_async": 0.013398380299866857,
14
- "base_inference_CO2_emissions": 4.072261623993283e-05,
15
- "base_inference_energy_consumption": 0.00011265253741674144,
16
  "smashed_current_gpu_type": "NVIDIA A100-PCIE-40GB",
17
  "smashed_current_gpu_total_memory": 40339.3125,
18
- "smashed_token_generation_latency_sync": 49.13712501525879,
19
- "smashed_token_generation_latency_async": 48.9015968516469,
20
- "smashed_token_generation_throughput_sync": 0.02035121101793125,
21
- "smashed_token_generation_throughput_async": 0.02044922997164503,
22
- "smashed_token_generation_CO2_emissions": 3.524599859739772e-05,
23
- "smashed_token_generation_energy_consumption": 0.009180102018160505,
24
- "smashed_inference_latency_sync": 52.06343727111816,
25
- "smashed_inference_latency_async": 49.8340368270874,
26
- "smashed_inference_throughput_sync": 0.019207337287250974,
27
- "smashed_inference_throughput_async": 0.0200666063531993,
28
- "smashed_inference_CO2_emissions": 3.379301910600281e-05,
29
- "smashed_inference_energy_consumption": 9.774841757057516e-05
30
  }
 
1
  {
2
  "base_current_gpu_type": "NVIDIA A100-PCIE-40GB",
3
  "base_current_gpu_total_memory": 40339.3125,
4
+ "base_token_generation_latency_sync": 57.667279434204104,
5
+ "base_token_generation_latency_async": 58.03066436201334,
6
+ "base_token_generation_throughput_sync": 0.017340856198027464,
7
+ "base_token_generation_throughput_async": 0.017232268680601154,
8
+ "base_token_generation_CO2_emissions": null,
9
+ "base_token_generation_energy_consumption": null,
10
+ "base_inference_latency_sync": 56.35584030151367,
11
+ "base_inference_latency_async": 55.629873275756836,
12
+ "base_inference_throughput_sync": 0.017744389838742956,
13
+ "base_inference_throughput_async": 0.017975953226479737,
14
+ "base_inference_CO2_emissions": null,
15
+ "base_inference_energy_consumption": null,
16
  "smashed_current_gpu_type": "NVIDIA A100-PCIE-40GB",
17
  "smashed_current_gpu_total_memory": 40339.3125,
18
+ "smashed_token_generation_latency_sync": 41.73652305603027,
19
+ "smashed_token_generation_latency_async": 41.733165830373764,
20
+ "smashed_token_generation_throughput_sync": 0.02395983006676249,
21
+ "smashed_token_generation_throughput_async": 0.023961757515941703,
22
+ "smashed_token_generation_CO2_emissions": null,
23
+ "smashed_token_generation_energy_consumption": null,
24
+ "smashed_inference_latency_sync": 51.78419189453125,
25
+ "smashed_inference_latency_async": 42.34201908111572,
26
+ "smashed_inference_throughput_sync": 0.01931091252783664,
27
+ "smashed_inference_throughput_async": 0.023617201581348155,
28
+ "smashed_inference_CO2_emissions": null,
29
+ "smashed_inference_energy_consumption": null
30
  }
smash_config.json CHANGED
@@ -2,19 +2,19 @@
2
  "api_key": null,
3
  "verify_url": "http://johnrachwan.pythonanywhere.com",
4
  "smash_config": {
5
- "pruners": "[]",
6
  "pruning_ratio": 0.0,
7
- "factorizers": "[]",
8
  "quantizers": "['awq']",
9
  "weight_quantization_bits": 4,
10
- "output_deviation": 0.01,
11
- "compilers": "[]",
12
  "static_batch": true,
13
  "static_shape": true,
14
  "controlnet": "None",
15
  "unet_dim": 4,
16
  "device": "cuda",
17
- "cache_dir": "/ceph/hdd/staff/charpent/.cache/models8o3cnft5",
18
  "batch_size": 1,
19
  "model_name": "McGill-NLP/Llama-3-8B-Web",
20
  "task": "text_text_generation",
 
2
  "api_key": null,
3
  "verify_url": "http://johnrachwan.pythonanywhere.com",
4
  "smash_config": {
5
+ "pruners": "None",
6
  "pruning_ratio": 0.0,
7
+ "factorizers": "None",
8
  "quantizers": "['awq']",
9
  "weight_quantization_bits": 4,
10
+ "output_deviation": 0.005,
11
+ "compilers": "None",
12
  "static_batch": true,
13
  "static_shape": true,
14
  "controlnet": "None",
15
  "unet_dim": 4,
16
  "device": "cuda",
17
+ "cache_dir": "/ceph/hdd/staff/charpent/.cache/modelsbok3a_hw",
18
  "batch_size": 1,
19
  "model_name": "McGill-NLP/Llama-3-8B-Web",
20
  "task": "text_text_generation",