-
- Downloads
Merge branch 'main' into wandb_logging
Showing
- .github/workflows/pytest_cpu_gha_runner.yaml 81 additions, 0 deletions.github/workflows/pytest_cpu_gha_runner.yaml
- .vscode/settings.json 11 additions, 0 deletions.vscode/settings.json
- README.md 62 additions, 23 deletionsREADME.md
- benchmarks/inference/README.md 55 additions, 0 deletionsbenchmarks/inference/README.md
- benchmarks/inference/on-prem/README.md 38 additions, 0 deletionsbenchmarks/inference/on-prem/README.md
- benchmarks/inference/on-prem/vllm/chat_vllm_benchmark.py 205 additions, 0 deletionsbenchmarks/inference/on-prem/vllm/chat_vllm_benchmark.py
- benchmarks/inference/on-prem/vllm/input.jsonl 9 additions, 0 deletionsbenchmarks/inference/on-prem/vllm/input.jsonl
- benchmarks/inference/on-prem/vllm/parameters.json 15 additions, 0 deletionsbenchmarks/inference/on-prem/vllm/parameters.json
- benchmarks/inference/on-prem/vllm/pretrained_vllm_benchmark.py 215 additions, 0 deletions...marks/inference/on-prem/vllm/pretrained_vllm_benchmark.py
- benchmarks/inference/tokenizer/special_tokens_map.json 23 additions, 0 deletionsbenchmarks/inference/tokenizer/special_tokens_map.json
- benchmarks/inference/tokenizer/tokenizer.json 93391 additions, 0 deletionsbenchmarks/inference/tokenizer/tokenizer.json
- benchmarks/inference/tokenizer/tokenizer.model 0 additions, 0 deletionsbenchmarks/inference/tokenizer/tokenizer.model
- benchmarks/inference/tokenizer/tokenizer_config.json 35 additions, 0 deletionsbenchmarks/inference/tokenizer/tokenizer_config.json
- benchmarks/inference_throughput/cloud-api/README.md 30 additions, 0 deletionsbenchmarks/inference_throughput/cloud-api/README.md
- benchmarks/inference_throughput/cloud-api/azure/chat_azure_api_benchmark.py 133 additions, 0 deletions...ce_throughput/cloud-api/azure/chat_azure_api_benchmark.py
- benchmarks/inference_throughput/cloud-api/azure/input.jsonl 9 additions, 0 deletionsbenchmarks/inference_throughput/cloud-api/azure/input.jsonl
- benchmarks/inference_throughput/cloud-api/azure/parameters.json 12 additions, 0 deletions...arks/inference_throughput/cloud-api/azure/parameters.json
- benchmarks/inference_throughput/cloud-api/azure/pretrained_azure_api_benchmark.py 142 additions, 0 deletions...oughput/cloud-api/azure/pretrained_azure_api_benchmark.py
- benchmarks/inference_throughput/requirements.txt 5 additions, 0 deletionsbenchmarks/inference_throughput/requirements.txt
- demo_apps/Azure_API_example/azure_api_example.ipynb 610 additions, 0 deletionsdemo_apps/Azure_API_example/azure_api_example.ipynb
Loading
Please register or sign in to comment