[Docs] Remove Inkling H200 LoRA BF16 cookbook command (#31489)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Fable 5
parent
8c9833f9a9
commit
68f4de162d
@@ -1054,37 +1054,5 @@ export const config = {
|
||||
"--port {{PORT}}",
|
||||
],
|
||||
},
|
||||
{
|
||||
match: { hw: "h200", variant: "lora", quant: "bf16", strategy: "balanced", nodes: "single" },
|
||||
env: [
|
||||
"SGLANG_ENABLE_UNIFIED_RADIX_TREE=1",
|
||||
"SGLANG_EXPERIMENTAL_LORA_OPTI=1",
|
||||
"SGLANG_OPT_LORA_OVERLAP_MAIN_ALLOC=1",
|
||||
],
|
||||
flags: [
|
||||
"--trust-remote-code",
|
||||
"--model-path {{MODEL_NAME}}",
|
||||
"--tp 8",
|
||||
"--moe-runner-backend triton",
|
||||
"--attention-backend fa4",
|
||||
"--page-size 128",
|
||||
"--enable-torch-symm-mem",
|
||||
"--mamba-radix-cache-strategy extra_buffer",
|
||||
"--mem-fraction-static 0.87",
|
||||
"--swa-full-tokens-ratio 0.1",
|
||||
"--mamba-full-memory-ratio 0.1",
|
||||
"--enable-multimodal",
|
||||
"--reasoning-parser inkling",
|
||||
"--tool-call-parser inkling",
|
||||
"--enable-lora",
|
||||
"--disable-prefill-cuda-graph",
|
||||
"--lora-backend triton",
|
||||
"--lora-use-virtual-experts",
|
||||
"--max-loras-per-batch {{MAX_LORAS}}",
|
||||
"--lora-paths lora0={{ADAPTER_PATH}}",
|
||||
"--host {{HOST_IP}}",
|
||||
"--port {{PORT}}",
|
||||
],
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
Reference in New Issue
Block a user