first version of example ready

This commit is contained in:
Kyle Corbitt
2023-08-25 06:37:06 +00:00
parent 40638a7848
commit b4cb931f6c
4 changed files with 31 additions and 492 deletions

View File

@@ -159,15 +159,15 @@
"name": "stdout",
"output_type": "stream",
"text": [
"INFO 08-24 22:01:58 llm_engine.py:70] Initializing an LLM engine with config: model='./models/run1/merged', tokenizer='./models/run1/merged', tokenizer_mode=auto, trust_remote_code=False, dtype=torch.float16, use_dummy_weights=False, download_dir=None, use_np_weights=False, tensor_parallel_size=1, seed=0)\n",
"INFO 08-24 22:02:46 llm_engine.py:196] # GPU blocks: 3419, # CPU blocks: 512\n"
"INFO 08-25 03:58:49 llm_engine.py:70] Initializing an LLM engine with config: model='./models/run1/merged', tokenizer='./models/run1/merged', tokenizer_mode=auto, trust_remote_code=False, dtype=torch.float16, use_dummy_weights=False, download_dir=None, use_np_weights=False, tensor_parallel_size=1, seed=0)\n",
"INFO 08-25 03:59:40 llm_engine.py:196] # GPU blocks: 3419, # CPU blocks: 512\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Processed prompts: 100%|██████████| 500/500 [00:37<00:00, 13.44it/s]"
"Processed prompts: 100%|██████████| 500/500 [00:37<00:00, 13.42it/s]"
]
},
{
@@ -216,7 +216,7 @@
},
{
"cell_type": "code",
"execution_count": 26,
"execution_count": 5,
"metadata": {},
"outputs": [
{
@@ -266,7 +266,7 @@
},
{
"cell_type": "code",
"execution_count": 35,
"execution_count": 6,
"metadata": {},
"outputs": [
{
@@ -629,6 +629,13 @@
"\n",
"Interested in cost/latency benchmarking? You can check out [./benchmarking.ipynb](./benchmarking.ipynb) for an overview of my findings!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {