Walkthrough

This pull request introduces support for Mamba SSM stochastic rounding by adding a new configuration field that flows from CLI arguments through config classes to the Mamba2 mixer implementation. The change includes conditional routing logic between FlashInfer and native execution paths based on hardware capabilities and dtype constraints. The FlashInfer dependency is updated to an URL-based installation reference.

Changes

Sequence Diagram

sequenceDiagram
    actor User
    participant CLI as CLI Parser
    participant KvCache as KvCacheConfig
    participant Loader as ModelLoader
    participant QuantCfg as QuantConfig
    participant Mixer as Mamba2Mixer
    
    User->>CLI: --mamba_ssm_stochastic_rounding flag
    CLI->>KvCache: args.mamba_ssm_stochastic_rounding
    KvCache->>Loader: kv_cache_config.mamba_ssm_stochastic_rounding
    Loader->>QuantCfg: validate_and_set_mamba_ssm_cache_dtype()
    QuantCfg->>QuantCfg: Set mamba_ssm_stochastic_rounding
    QuantCfg->>Mixer: config.mamba_ssm_stochastic_rounding
    
    Mixer->>Mixer: Check head_dim in [64, 128]?
    Mixer->>Mixer: Check dtype == float16?
    Mixer->>Mixer: Check FlashInfer available?
    
    alt All conditions met
        Mixer->>Mixer: _use_stochastic_rounding = True
        Mixer->>Mixer: Add rand_seed to kwargs
    else Conditions not met
        Mixer->>Mixer: _use_stochastic_rounding = False
        Mixer->>Mixer: Emit warning
    end
    
    alt _use_flashinfer enabled
        Mixer->>Mixer: Route to FlashInfer path
    else
        Mixer->>Mixer: Route to native implementation
    end

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

❌ Failed checks (1 warning, 1 inconclusive)

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental) --high-priority]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

--high-priority (OPTIONAL) : Run the pipeline with high priority. This option is restricted to authorized users only and will route the job to a high-priority queue.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.