Skip to content

Qwen3 model #1311

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Oct 14, 2025
Merged

Qwen3 model #1311

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
049f8c4
Qwen3 model
lastshogun13 Oct 5, 2025
002bc89
Merge branch 'main' into feature/qwen3-model
lastshogun13 Oct 11, 2025
c15b16e
fix max token
lastshogun13 Oct 11, 2025
da06830
remove comment
lastshogun13 Oct 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions docs/en/DEPLOY_OPTION.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -980,6 +980,10 @@ This solution supports the following text generation models:
"apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
"apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
"us.deepseek.r1-v1:0",
"qwen.qwen3-235b-a22b-2507-v1:0",
"qwen.qwen3-32b-v1:0",
"qwen.qwen3-coder-480b-a35b-v1:0",
"qwen.qwen3-coder-30b-a3b-v1:0",
"us.writer.palmyra-x5-v1:0",
"us.writer.palmyra-x4-v1:0",
"amazon.titan-text-premier-v1:0",
Expand Down
4 changes: 4 additions & 0 deletions docs/ja/DEPLOY_OPTION.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -995,6 +995,10 @@ const envs: Record<string, Partial<StackInput>> = {
"apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
"apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
"us.deepseek.r1-v1:0",
"qwen.qwen3-235b-a22b-2507-v1:0",
"qwen.qwen3-32b-v1:0",
"qwen.qwen3-coder-480b-a35b-v1:0",
"qwen.qwen3-coder-30b-a3b-v1:0",
"us.writer.palmyra-x5-v1:0",
"us.writer.palmyra-x4-v1:0",
"amazon.titan-text-premier-v1:0",
Expand Down
4 changes: 4 additions & 0 deletions docs/ko/DEPLOY_OPTION.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -976,6 +976,10 @@ const envs: Record<string, Partial<StackInput>> = {
"apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
"apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
"us.deepseek.r1-v1:0",
"qwen.qwen3-235b-a22b-2507-v1:0",
"qwen.qwen3-32b-v1:0",
"qwen.qwen3-coder-480b-a35b-v1:0",
"qwen.qwen3-coder-30b-a3b-v1:0",
"us.writer.palmyra-x5-v1:0",
"us.writer.palmyra-x4-v1:0",
"amazon.titan-text-premier-v1:0",
Expand Down
57 changes: 57 additions & 0 deletions packages/cdk/lambda/utils/models.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,6 +206,31 @@ const DEEPSEEK_DEFAULT_PARAMS: ConverseInferenceParams = {
},
};

// Qwen3 model parameters based on actual AWS Bedrock limits
const QWEN_16K_DEFAULT_PARAMS: ConverseInferenceParams = {
inferenceConfig: {
maxTokens: 16384,
temperature: 0.7,
topP: 0.9,
},
};

const QWEN_64K_DEFAULT_PARAMS: ConverseInferenceParams = {
inferenceConfig: {
maxTokens: 65536,
temperature: 0.7,
topP: 0.9,
},
};

const QWEN_192K_DEFAULT_PARAMS: ConverseInferenceParams = {
inferenceConfig: {
maxTokens: 196608,
temperature: 0.7,
topP: 0.9,
},
};

const PALMYRA_DEFAULT_PARAMS: ConverseInferenceParams = {
inferenceConfig: {
maxTokens: 8192,
Expand Down Expand Up @@ -1491,6 +1516,38 @@ export const BEDROCK_TEXT_GEN_MODELS: {
extractConverseOutput: extractConverseOutput,
extractConverseStreamOutput: extractConverseStreamOutput,
},
'qwen.qwen3-235b-a22b-2507-v1:0': {
defaultParams: QWEN_192K_DEFAULT_PARAMS,
usecaseParams: USECASE_DEFAULT_PARAMS,
createConverseCommandInput: createConverseCommandInput,
createConverseStreamCommandInput: createConverseStreamCommandInput,
extractConverseOutput: extractConverseOutput,
extractConverseStreamOutput: extractConverseStreamOutput,
},
'qwen.qwen3-32b-v1:0': {
defaultParams: QWEN_16K_DEFAULT_PARAMS,
usecaseParams: USECASE_DEFAULT_PARAMS,
createConverseCommandInput: createConverseCommandInput,
createConverseStreamCommandInput: createConverseStreamCommandInput,
extractConverseOutput: extractConverseOutput,
extractConverseStreamOutput: extractConverseStreamOutput,
},
'qwen.qwen3-coder-480b-a35b-v1:0': {
defaultParams: QWEN_64K_DEFAULT_PARAMS,
usecaseParams: USECASE_DEFAULT_PARAMS,
createConverseCommandInput: createConverseCommandInput,
createConverseStreamCommandInput: createConverseStreamCommandInput,
extractConverseOutput: extractConverseOutput,
extractConverseStreamOutput: extractConverseStreamOutput,
},
'qwen.qwen3-coder-30b-a3b-v1:0': {
defaultParams: QWEN_192K_DEFAULT_PARAMS,
usecaseParams: USECASE_DEFAULT_PARAMS,
createConverseCommandInput: createConverseCommandInput,
createConverseStreamCommandInput: createConverseStreamCommandInput,
extractConverseOutput: extractConverseOutput,
extractConverseStreamOutput: extractConverseStreamOutput,
},
// Although Palmyra supports system context, the model seems work best without it.
'us.writer.palmyra-x4-v1:0': {
defaultParams: PALMYRA_DEFAULT_PARAMS,
Expand Down
17 changes: 17 additions & 0 deletions packages/common/src/application/model.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -384,6 +384,23 @@ export const modelMetadata: Record<string, ModelMetadata> = {
flags: MODEL_FEATURE.TEXT_DOC_REASONING,
displayName: 'DeepSeek-R1',
},
// Qwen
'qwen.qwen3-235b-a22b-2507-v1:0': {
flags: MODEL_FEATURE.TEXT_ONLY,
displayName: 'Qwen3 235B A22B 2507',
},
'qwen.qwen3-32b-v1:0': {
flags: MODEL_FEATURE.TEXT_ONLY,
displayName: 'Qwen3 32B',
},
'qwen.qwen3-coder-480b-a35b-v1:0': {
flags: MODEL_FEATURE.TEXT_ONLY,
displayName: 'Qwen3-Coder 480B A35B Instruct',
},
'qwen.qwen3-coder-30b-a3b-v1:0': {
flags: MODEL_FEATURE.TEXT_ONLY,
displayName: 'Qwen3-Coder 30B A3B Instruct',
},
// Writer
'us.writer.palmyra-x4-v1:0': {
flags: MODEL_FEATURE.TEXT_DOC,
Expand Down