KvCacheManagerV2 segfault on ~256k prompts with Nemotron-3-Ultra when max_seq_len=1M and avg_seq_len unset

[Bug]: DGX Spark playbook supported models fail in trtllm-serve: Nemotron-3 Nano Omni and GPT-OSS rejected as unsupported due to MODEL_MAP registry mismatch

[Bug]: Clamp very small non-zero temperature values to avoid numerical instability

[Bug]: Gemma4 multimodal serving — two startup crashes (vision tp_size>1, xgrammar guided decoding)

[AutoDeploy] Re-enable SSM replay for Nemotron-Super MTP (replay kernel illegal memory access at CUDA-graph capture on Blackwell)

[Parity with vLLM, SGLang, ATOM]: Public Nightly NGC docker images too

[Bug]: Qwen3.5-397B-A17B (bf16) OOMs host RAM on the PyTorch backend; AutoDeploy loads fine on the same node

[Feature Request] AutoDeploy: enable DeepSeek R1 MTP

[Bug]: Guided decoding with Kimi-K2.5

[Feature]: Investigate the unstable perf of llama 3.1 8B fp8 in CI test_sanity_perf.py