diff --git a/docs_new/src/snippets/configs/thinkingmachines/inkling.jsx b/docs_new/src/snippets/configs/thinkingmachines/inkling.jsx index ec67776d7..f2b3f66d4 100644 --- a/docs_new/src/snippets/configs/thinkingmachines/inkling.jsx +++ b/docs_new/src/snippets/configs/thinkingmachines/inkling.jsx @@ -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}}", - ], - }, ], };