[V1] [Hybrid] Enable piecewise CUDA Graph for mamba layers (#21194)

Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
This commit is contained in:
Thomas Parnell
2025-07-19 19:27:21 +00:00
committed by GitHub
parent 9f414a12ad
commit 881e3cbe3b
10 changed files with 100 additions and 31 deletions
-3
View File
@@ -2753,9 +2753,6 @@ class GPUModelRunner(LoRAModelRunnerMixin):
if self.vllm_config.speculative_config is not None:
raise NotImplementedError(
"Mamba with speculative decoding is not supported yet.")
if not self.vllm_config.model_config.enforce_eager:
raise NotImplementedError(
"Mamba with cuda graph is not supported yet.")
if self.vllm_config.cache_config.enable_prefix_caching:
raise NotImplementedError(
"Prefix caching is not supported for Mamba yet.")