[Compilation Bug] Fix Inductor Graph Output with Shape Issue (vllm-pr…

…oject#24772)

Signed-off-by: yewentao256 <[email protected]>

Merge branch 'main' into wye-refactor-quant-folder

[Bugfix] fixes the causal_conv1d_update kernel update non-speculative…

… decoding cases (vllm-project#24680)

Signed-off-by: Tao He <[email protected]>
Co-authored-by: Cyrus Leung <[email protected]>

[CI] execute all piecewise compilation tests together (vllm-project#2…

…4502)

Signed-off-by: zjy0516 <[email protected]>

Do not use eval() to convert unknown types (vllm-project#23266)

Signed-off-by: Russell Bryant <[email protected]>
Signed-off-by: simon-mo <[email protected]>

Use Blackwell FlashInfer MXFP4 MoE by default if available (vllm-proj…

…ect#23008)

Signed-off-by: mgoin <[email protected]>

fix: gptq marlin weight loading failure (vllm-project#23066)

Add think chunk (vllm-project#21333)

Signed-off-by: Julien Denize <[email protected]>

Add think chunk (vllm-project#21333)

Signed-off-by: Julien Denize <[email protected]>

Enable v1 metrics tests (vllm-project#20953)

Signed-off-by: Seiji Eicher <[email protected]>