From 430f38ea2530453c0940b94da8251adf2d0ea047 Mon Sep 17 00:00:00 2001 From: Ke Bao Date: Mon, 10 Aug 2026 17:12:51 +0800 Subject: [PATCH] Update dspark draft path in Inkling small cookbook (#34250) --- .../autoregressive/ThinkingMachines/Inkling-Small.mdx | 2 +- .../snippets/configs/thinkingmachines/inkling-small.jsx | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/cookbook/autoregressive/ThinkingMachines/Inkling-Small.mdx b/docs/cookbook/autoregressive/ThinkingMachines/Inkling-Small.mdx index 63593844c..d95e1ecab 100644 --- a/docs/cookbook/autoregressive/ThinkingMachines/Inkling-Small.mdx +++ b/docs/cookbook/autoregressive/ThinkingMachines/Inkling-Small.mdx @@ -307,6 +307,6 @@ To try it, select the **Long Context** strategy in the Deploy panel above for an ### 3.7 DSpark (Speculative Decoding) -The **DSpark** deploy strategy is the second speculative-decoding path for Inkling-Small. Unlike **MTP**, which drives Inkling-Small's own multi-layer draft head, DSpark runs a **separate draft checkpoint** — `RadixArk/Inkling-Small-DSpark-Preview` — served unquantized alongside the NVFP4 target. +The **DSpark** deploy strategy is the second speculative-decoding path for Inkling-Small. Unlike **MTP**, which drives Inkling-Small's own multi-layer draft head, DSpark runs a **separate draft checkpoint** — `RadixArk/Inkling-Small-DSpark` — served unquantized alongside the NVFP4 target. DSpark support ships in the images listed in §1 (`dev-inkling-dspark` for CUDA 13, `dev-cu12-inkling-dspark` for CUDA 12), so no separate build is needed. Verified end-to-end on B200 (TP=8, NVFP4). diff --git a/docs/src/snippets/configs/thinkingmachines/inkling-small.jsx b/docs/src/snippets/configs/thinkingmachines/inkling-small.jsx index dcc57fd47..40b019389 100644 --- a/docs/src/snippets/configs/thinkingmachines/inkling-small.jsx +++ b/docs/src/snippets/configs/thinkingmachines/inkling-small.jsx @@ -751,7 +751,7 @@ export const config = { "--tool-call-parser inkling", "--skip-server-warmup", "--speculative-algorithm DSPARK", - "--speculative-draft-model-path RadixArk/Inkling-Small-DSpark-Preview", + "--speculative-draft-model-path RadixArk/Inkling-Small-DSpark", "--speculative-draft-model-quantization unquant", "--chunked-prefill-size 8192", "--cuda-graph-max-bs-prefill 8192", @@ -786,7 +786,7 @@ export const config = { "--tool-call-parser inkling", "--skip-server-warmup", "--speculative-algorithm DSPARK", - "--speculative-draft-model-path RadixArk/Inkling-Small-DSpark-Preview", + "--speculative-draft-model-path RadixArk/Inkling-Small-DSpark", "--speculative-draft-model-quantization unquant", "--chunked-prefill-size 8192", "--cuda-graph-max-bs-prefill 8192", @@ -821,7 +821,7 @@ export const config = { "--tool-call-parser inkling", "--skip-server-warmup", "--speculative-algorithm DSPARK", - "--speculative-draft-model-path RadixArk/Inkling-Small-DSpark-Preview", + "--speculative-draft-model-path RadixArk/Inkling-Small-DSpark", "--speculative-draft-model-quantization unquant", "--chunked-prefill-size 8192", "--cuda-graph-max-bs-prefill 8192", @@ -856,7 +856,7 @@ export const config = { "--tool-call-parser inkling", "--skip-server-warmup", "--speculative-algorithm DSPARK", - "--speculative-draft-model-path RadixArk/Inkling-Small-DSpark-Preview", + "--speculative-draft-model-path RadixArk/Inkling-Small-DSpark", "--speculative-draft-model-quantization unquant", "--chunked-prefill-size 8192", "--cuda-graph-max-bs-prefill 8192",