docs: link dots3.note checkpoints, add H100 cells (#34797)
Co-authored-by: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -46,16 +46,12 @@ For how to launch the image, see [Install → Method 3: Using Docker](../../../d
|
||||
|
||||
</Accordion>
|
||||
|
||||
Pick the checkpoint precision — the only deployment choice. The recipe runs on a single 8-GPU H200 node with DP8 attention × TP8 × EP8 and DeepEP as the MoE all-to-all transport. Blackwell is not supported yet.
|
||||
Pick the hardware and the checkpoint precision. The recipe runs on a single 8-GPU Hopper node with DP8 attention × TP8 × EP8 and DeepEP as the MoE all-to-all transport. Blackwell is not supported yet.
|
||||
|
||||
**Precision** — selects the MoE path, not just the weights. The BF16 cells pin `--moe-runner-backend deep_gemm` with BF16 DeepEP dispatch output (JIT DeepGEMM is enabled via `SGLANG_ENABLE_JIT_DEEPGEMM=1`). The FP8 cells leave both at `auto` and let SGLang resolve the runner from the checkpoint's quantization config.
|
||||
|
||||
**Spec Decode** — NEXTN is on in every cell: 3 draft steps, 4 draft tokens per step, and the draft model path pointing at the target checkpoint itself. dots3's MTP layer is full-sharing — it carries the dots3 sliding-window attention geometry and reuses the target LM head — so no separate draft checkpoint is needed. Target verification and draft extension run on the paged, absorbed SWA-MLA FA3 path.
|
||||
|
||||
<Note>
|
||||
Every cell in the Deploy panel above is currently **unverified**: the recipe runs, but no serving round on public weights has landed (the checkpoint is not yet released). Treat the cells as starting points and re-measure throughput and accuracy on your workload.
|
||||
</Note>
|
||||
|
||||
import { Deployment } from "/src/snippets/_deployment.jsx";
|
||||
import { config } from "/src/snippets/configs/rednote/dots3-note.jsx";
|
||||
|
||||
@@ -70,13 +66,7 @@ dots3.note is RedNote's native multimodal omni model, built on the dots3 languag
|
||||
- **Hybrid attention** — dots3 combines MLA with full-attention and sliding-window layers of different geometry, attention gates, and optional DSA indexing on full-attention layers.
|
||||
- **MTP speculative decoding** — a full-sharing MTP/NextN architecture exposes one recursively shared, SWA-shaped MTP layer and shares the target LM head.
|
||||
|
||||
<Note>
|
||||
The dots3.note checkpoint is **not yet publicly released**. The recipes on this page were validated against [SGLang PR #33829](https://github.com/sgl-project/sglang/pull/33829); a Hugging Face repository will be linked here at launch.
|
||||
</Note>
|
||||
|
||||
**Resources:** [SGLang PR #33829](https://github.com/sgl-project/sglang/pull/33829)
|
||||
|
||||
{/* TODO: Add the Hugging Face link once the checkpoint is released. */}
|
||||
**Resources:** [Hugging Face](https://huggingface.co/dots-studio/dots3-note-prev) · [SGLang PR #33829](https://github.com/sgl-project/sglang/pull/33829)
|
||||
|
||||
## 2. Configuration Tips
|
||||
|
||||
|
||||
@@ -39,7 +39,8 @@
|
||||
// `verificationStatus` overrides it with a third state —
|
||||
// "verified" | "in-progress" | "unverified" — for a recipe
|
||||
// whose verification round is open rather than absent.
|
||||
// modelNames HF slug lookup, `hw|variant|quant` then `variant|quant`
|
||||
// modelNames HF slug lookup, `hw|variant|quant`, `variant|quant`,
|
||||
// `hw|quant`, `quant`, `hw`, then `default`
|
||||
// placeholders {{KEY}} → {target: 'command'|'curl', label, default?}
|
||||
// curl cURL template (uses {{MODEL_NAME}} + placeholders), or
|
||||
// `(selection, cell) => template` when the request payload
|
||||
@@ -643,10 +644,15 @@ export const Deployment = ({ config, benchmarks }) => {
|
||||
|
||||
// Lookup walks most-specific to least so a config that drops the variant/quant
|
||||
// dims can key its HF slug on `hw` alone, or on the single "default" entry.
|
||||
// The `hw|quant` and bare `quant` rungs cover a `matchDims` config that declares
|
||||
// no variant dim at all — there `sel.variant` is undefined, so the two leading
|
||||
// keys can never hit.
|
||||
const resolveModelName = (sel) => {
|
||||
const keys = [
|
||||
`${sel.hw}|${sel.variant}|${sel.quant}`,
|
||||
`${sel.variant}|${sel.quant}`,
|
||||
`${sel.hw}|${sel.quant}`,
|
||||
sel.quant,
|
||||
sel.hw,
|
||||
"default",
|
||||
];
|
||||
|
||||
@@ -171,11 +171,19 @@ export const Playground = ({ config }) => {
|
||||
return null;
|
||||
};
|
||||
|
||||
// hw|variant|quant → variant|quant → "".
|
||||
// hw|variant|quant → variant|quant → hw|quant → quant → "".
|
||||
const resolveModelName = (sel) => {
|
||||
const triple = `${sel.hw}|${sel.variant}|${sel.quant}`;
|
||||
const pair = `${sel.variant}|${sel.quant}`;
|
||||
return config.modelNames[triple] ?? config.modelNames[pair] ?? "";
|
||||
const keys = [
|
||||
`${sel.hw}|${sel.variant}|${sel.quant}`,
|
||||
`${sel.variant}|${sel.quant}`,
|
||||
`${sel.hw}|${sel.quant}`,
|
||||
sel.quant,
|
||||
];
|
||||
for (const k of keys) {
|
||||
const hit = config.modelNames[k];
|
||||
if (hit) return hit;
|
||||
}
|
||||
return "";
|
||||
};
|
||||
|
||||
const interpolate = (text, env, modelName) =>
|
||||
|
||||
@@ -9,7 +9,7 @@ export const config = {
|
||||
showPlaygroundLink: false,
|
||||
|
||||
// Hopper only for now — no Blackwell support.
|
||||
supportedHardware: ["h200"],
|
||||
supportedHardware: ["h200", "h100"],
|
||||
|
||||
// One model and one node shape — only the checkpoint precision is a real choice.
|
||||
matchDims: [
|
||||
@@ -24,8 +24,8 @@ export const config = {
|
||||
],
|
||||
|
||||
modelNames: {
|
||||
// TODO: replace with the public repo id once the checkpoint is released.
|
||||
default: "<dots-note-checkpoint>",
|
||||
bf16: "dots-studio/dots3-note-prev",
|
||||
fp8: "dots-studio/dots3-note-prev-fp8",
|
||||
},
|
||||
|
||||
placeholders: {
|
||||
@@ -55,6 +55,7 @@ export const config = {
|
||||
|
||||
dockerImages: {
|
||||
h200: "lmsysorg/sglang:dev",
|
||||
h100: "lmsysorg/sglang:dev",
|
||||
},
|
||||
|
||||
|
||||
@@ -62,6 +63,108 @@ export const config = {
|
||||
{
|
||||
match: { hw: "h200", quant: "bf16" },
|
||||
nnodes: 1,
|
||||
verified: true,
|
||||
env: [
|
||||
"SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1",
|
||||
"SGLANG_ENABLE_JIT_DEEPGEMM=1",
|
||||
"SGLANG_CHUNKED_PREFIX_CACHE_THRESHOLD=8192",
|
||||
"SGLANG_MAX_KV_CHUNK_CAPACITY=8192",
|
||||
"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128",
|
||||
"SGLANG_WARMUP_TIMEOUT=1800",
|
||||
],
|
||||
flags: [
|
||||
"--model-path {{MODEL_NAME}}",
|
||||
"--context-length 524288",
|
||||
"--enable-dp-attention",
|
||||
"--dp-size 8",
|
||||
"--tp-size 8",
|
||||
"--ep-size 8",
|
||||
"--mem-fraction-static 0.87",
|
||||
"--max-running-requests 256",
|
||||
"--chunked-prefill-size 16384",
|
||||
"--trust-remote-code",
|
||||
"--swa-full-tokens-ratio 0.03",
|
||||
"--prefill-attention-backend fa3",
|
||||
"--decode-attention-backend fa3",
|
||||
"--page-size 64",
|
||||
"--moe-dense-tp-size 1",
|
||||
"--cuda-graph-backend-decode full",
|
||||
"--cuda-graph-backend-prefill disabled",
|
||||
"--cuda-graph-max-bs-decode 32",
|
||||
"--speculative-algorithm NEXTN",
|
||||
"--speculative-num-steps 3",
|
||||
"--speculative-eagle-topk 1",
|
||||
"--speculative-num-draft-tokens 4",
|
||||
"--speculative-draft-model-path {{MODEL_NAME}}",
|
||||
"--speculative-draft-attention-backend fa3",
|
||||
"--moe-a2a-backend deepep",
|
||||
"--moe-runner-backend deep_gemm",
|
||||
"--deepep-dispatcher-output-dtype bf16",
|
||||
"--deepep-mode auto",
|
||||
"--enable-nccl-nvls",
|
||||
"--enable-multimodal",
|
||||
"--enable-metrics",
|
||||
"--tool-call-parser dots",
|
||||
"--reasoning-parser qwen3",
|
||||
"--watchdog-timeout 1800",
|
||||
"--host {{HOST_IP}}",
|
||||
"--port {{PORT}}",
|
||||
],
|
||||
},
|
||||
{
|
||||
match: { hw: "h200", quant: "fp8" },
|
||||
nnodes: 1,
|
||||
verified: true,
|
||||
env: [
|
||||
"SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1",
|
||||
"SGLANG_ENABLE_JIT_DEEPGEMM=1",
|
||||
"SGLANG_CHUNKED_PREFIX_CACHE_THRESHOLD=8192",
|
||||
"SGLANG_MAX_KV_CHUNK_CAPACITY=8192",
|
||||
"SGLANG_DEEPEP_NUM_MAX_DISPATCH_TOKENS_PER_RANK=128",
|
||||
"SGLANG_WARMUP_TIMEOUT=1800",
|
||||
],
|
||||
flags: [
|
||||
"--model-path {{MODEL_NAME}}",
|
||||
"--context-length 524288",
|
||||
"--enable-dp-attention",
|
||||
"--dp-size 8",
|
||||
"--tp-size 8",
|
||||
"--ep-size 8",
|
||||
"--mem-fraction-static 0.87",
|
||||
"--max-running-requests 256",
|
||||
"--chunked-prefill-size 16384",
|
||||
"--trust-remote-code",
|
||||
"--swa-full-tokens-ratio 0.03",
|
||||
"--prefill-attention-backend fa3",
|
||||
"--decode-attention-backend fa3",
|
||||
"--page-size 64",
|
||||
"--moe-dense-tp-size 1",
|
||||
"--cuda-graph-backend-decode full",
|
||||
"--cuda-graph-backend-prefill disabled",
|
||||
"--cuda-graph-max-bs-decode 32",
|
||||
"--speculative-algorithm NEXTN",
|
||||
"--speculative-num-steps 3",
|
||||
"--speculative-eagle-topk 1",
|
||||
"--speculative-num-draft-tokens 4",
|
||||
"--speculative-draft-model-path {{MODEL_NAME}}",
|
||||
"--speculative-draft-attention-backend fa3",
|
||||
"--moe-a2a-backend deepep",
|
||||
"--moe-runner-backend auto",
|
||||
"--deepep-dispatcher-output-dtype auto",
|
||||
"--deepep-mode auto",
|
||||
"--enable-nccl-nvls",
|
||||
"--enable-multimodal",
|
||||
"--enable-metrics",
|
||||
"--reasoning-parser qwen3",
|
||||
"--tool-call-parser dots",
|
||||
"--watchdog-timeout 1800",
|
||||
"--host {{HOST_IP}}",
|
||||
"--port {{PORT}}",
|
||||
],
|
||||
},
|
||||
{
|
||||
match: { hw: "h100", quant: "bf16" },
|
||||
nnodes: 1,
|
||||
verified: false,
|
||||
env: [
|
||||
"SGLANG_ALLOW_OVERWRITE_LONGER_CONTEXT_LEN=1",
|
||||
@@ -111,7 +214,7 @@ export const config = {
|
||||
],
|
||||
},
|
||||
{
|
||||
match: { hw: "h200", quant: "fp8" },
|
||||
match: { hw: "h100", quant: "fp8" },
|
||||
nnodes: 1,
|
||||
verified: false,
|
||||
env: [
|
||||
|
||||
Reference in New Issue
Block a user