docs(ai): Remove old API reference from README
This commit is contained in:
@@ -114,7 +114,7 @@
|
||||
}
|
||||
}
|
||||
],
|
||||
"notes": "Requires vLLM 0.10.1+gptoss. Tools/functoin calls only via /v1/responses endpoint."
|
||||
"notes": "Tools/function calls only via /v1/responses endpoint."
|
||||
},
|
||||
"openai/gpt-oss-120b": {
|
||||
"name": "GPT-OSS-120B",
|
||||
@@ -123,25 +123,25 @@
|
||||
"gpuCount": 1,
|
||||
"gpuTypes": ["H100", "H200"],
|
||||
"args": ["--async-scheduling", "--gpu-memory-utilization", "0.95", "--max-num-batched-tokens", "1024"],
|
||||
"notes": "Single GPU deployment. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
|
||||
"notes": "Single GPU deployment. Tools/function calls only via /v1/responses endpoint."
|
||||
},
|
||||
{
|
||||
"gpuCount": 2,
|
||||
"gpuTypes": ["H100", "H200"],
|
||||
"args": ["--tensor-parallel-size", "2", "--async-scheduling", "--gpu-memory-utilization", "0.94"],
|
||||
"notes": "Recommended for H100/H200. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
|
||||
"notes": "Recommended for H100/H200. Tools/function calls only via /v1/responses endpoint."
|
||||
},
|
||||
{
|
||||
"gpuCount": 4,
|
||||
"gpuTypes": ["H100", "H200"],
|
||||
"args": ["--tensor-parallel-size", "4", "--async-scheduling"],
|
||||
"notes": "Higher throughput. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
|
||||
"notes": "Higher throughput. Tools/function calls only via /v1/responses endpoint."
|
||||
},
|
||||
{
|
||||
"gpuCount": 8,
|
||||
"gpuTypes": ["H100", "H200"],
|
||||
"args": ["--tensor-parallel-size", "8", "--async-scheduling"],
|
||||
"notes": "Maximum throughput for evaluation workloads. Requires vLLM 0.10.1+gptoss. Tools/function calls only via /v1/responses endpoint."
|
||||
"notes": "Maximum throughput for evaluation workloads. Tools/function calls only via /v1/responses endpoint."
|
||||
}
|
||||
]
|
||||
},
|
||||
|
||||
Reference in New Issue
Block a user