[Model] Complete dots.note.omni support with native encoders, video preprocessing, and MTP decoding (#33829)

Co-authored-by: miraclezqc <dysania@pku.edu.cn>
This commit is contained in:
Jianfei Wang
2026-08-22 14:19:14 +08:00
committed by GitHub
co-authored by miraclezqc
parent c35683fda0
commit af39ad9349
55 changed files with 9638 additions and 154 deletions
+112 -60
View File
@@ -1,13 +1,9 @@
// Dots3-Note cookbook config. Consumed by _deployment.jsx + _playground.jsx.
// Single `export const config` literal - no spreads/calls/IIFE (Mintlify re-evals at hydration).
// Single `export const config` literal — no spreads/calls/IIFE (Mintlify re-evals at hydration).
export const config = {
modelName: "Dots3-Note",
// No Playground on this page — the only extra knob (the dots tool-call parser)
// is already baked into the cells.
showPlaygroundLink: false,
// Hopper only for now — no Blackwell support.
supportedHardware: ["h200", "h100"],
@@ -50,14 +46,78 @@ export const config = {
{"type": "video_url", "video_url": {"url": "https://example.com/sample.mp4"}},
{"type": "text", "text": "Summarize what happens in this video."}
]
}]
}],
"video_config": {
"seq": 131072,
"audio_cap": 0.5,
"audio_sr": 16000,
"k_mode": "eval_ek"
}
}'`,
dockerImages: {
h200: "lmsysorg/sglang:dev",
h100: "lmsysorg/sglang:dev",
h200: "lmsysorg/sglang:dev-dots3-note",
h100: "lmsysorg/sglang:dev-dots3-note",
},
github: {
cookbookModel: "dots-studio/dots3-note-prev",
},
playgroundFeatures: {
attention: {
knobs: [
{ id: "tp", label: "TP", values: [null, 4, 8] },
{
id: "dpAttn",
label: "DP-Attention",
values: [null, false, 4, 8],
labels: { "auto": "Auto", "false": "Off" },
},
],
},
moe: {
backend: {
options: [
{ id: null, label: "Inherited" },
{ id: "deepep", label: "DeepEP", flags: ["--moe-a2a-backend deepep"] },
],
},
ep: { label: "EP", values: [null, 4, 8] },
},
parsers: {
items: [
{
id: "reasoning",
label: "Reasoning Parser",
flag: "--reasoning-parser dots",
},
{
id: "toolCall",
label: "Tool Call Parser",
flag: "--tool-call-parser dots",
},
],
},
speculative: {
options: [
{ id: "current", label: "Inherited from base" },
{ id: "off", label: "Off (greedy)" },
{
id: "nextn-314",
label: "NEXTN / MTP 3-1-4",
flags: [
"--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",
],
},
],
},
},
cells: [
{
@@ -74,20 +134,25 @@ export const config = {
],
flags: [
"--model-path {{MODEL_NAME}}",
"--context-length 524288",
"--trust-remote-code",
"--enable-dp-attention",
"--dp-size 8",
"--tp-size 8",
"--ep-size 8",
"--tp 8",
"--dp 8",
"--ep 8",
"--moe-dense-tp-size 1",
"--moe-a2a-backend deepep",
"--moe-runner-backend deep_gemm",
"--deepep-dispatcher-output-dtype bf16",
"--deepep-mode auto",
"--enable-nccl-nvls",
"--context-length 524288",
"--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",
@@ -97,15 +162,8 @@ export const config = {
"--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}}",
@@ -125,20 +183,25 @@ export const config = {
],
flags: [
"--model-path {{MODEL_NAME}}",
"--context-length 524288",
"--trust-remote-code",
"--enable-dp-attention",
"--dp-size 8",
"--tp-size 8",
"--ep-size 8",
"--tp 8",
"--dp 8",
"--ep 8",
"--moe-dense-tp-size 1",
"--moe-a2a-backend deepep",
"--moe-runner-backend auto",
"--deepep-dispatcher-output-dtype auto",
"--deepep-mode auto",
"--enable-nccl-nvls",
"--context-length 524288",
"--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",
@@ -148,15 +211,8 @@ export const config = {
"--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}}",
@@ -176,20 +232,25 @@ export const config = {
],
flags: [
"--model-path {{MODEL_NAME}}",
"--context-length 524288",
"--trust-remote-code",
"--enable-dp-attention",
"--dp-size 8",
"--tp-size 8",
"--ep-size 8",
"--tp 8",
"--dp 8",
"--ep 8",
"--moe-dense-tp-size 1",
"--moe-a2a-backend deepep",
"--moe-runner-backend deep_gemm",
"--deepep-dispatcher-output-dtype bf16",
"--deepep-mode auto",
"--enable-nccl-nvls",
"--context-length 524288",
"--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",
@@ -199,15 +260,8 @@ export const config = {
"--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}}",
@@ -227,20 +281,25 @@ export const config = {
],
flags: [
"--model-path {{MODEL_NAME}}",
"--context-length 524288",
"--trust-remote-code",
"--enable-dp-attention",
"--dp-size 8",
"--tp-size 8",
"--ep-size 8",
"--tp 8",
"--dp 8",
"--ep 8",
"--moe-dense-tp-size 1",
"--moe-a2a-backend deepep",
"--moe-runner-backend auto",
"--deepep-dispatcher-output-dtype auto",
"--deepep-mode auto",
"--enable-nccl-nvls",
"--context-length 524288",
"--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",
@@ -250,15 +309,8 @@ export const config = {
"--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}}",