[Bugfix][Core] Fall back when numactl --membind is blocked in constrained containers (#45438)

Ting SUN committed 5 months ago

[Model] Remove Dots1ForCausalLM (#45637)

Tiezhen WANG committed 5 months ago

[Model Runner V2] Enable GraniteMOE for MRv2 by default (#45461)

Wentao Ye committed 5 months ago

[ROCm][CI] Patch conftest to resolve occasional OOMs (#45722)

Micah Williamson committed 5 months ago

Upgrade tpu-inference to v0.22.1 (#45793)

Sting Lin committed 5 months ago

[Model] Add HrmTextForCausalLM (Hierarchical Reasoning Model — Text) (#43098)

yifei wu committed 5 months ago

[ROCm][Cleanup] Remove stale AITER FA hybrid KV-cache TODO (#44178)

Tuukka Sarvi committed 5 months ago

feat: MLA prefill enable FA4 fp8 output (#43050)

Carl Y committed 5 months ago

[Kernel][Helion][1/N] Add Helion kernel for rms_norm_per_block_quant (#36895)

Xiaohong (Sean) Chen committed 5 months ago

[Bugfix] Fix FlashMLA sparse accuracy with topk_length and zero-init padding (#36616)

Ajay Anubolu committed 5 months ago

[Rust Frontend] Add CORS support (#45753)

Tahsin Tunan committed 5 months ago

[CI] Fix attention benchmark smoke test (#45728)

Matthew Bonanni committed 5 months ago

[Perf] Add VLLM_TRITON_FORCE_FIRST_CONFIG to skip Triton autotuning (#42425)

Francesco Fusco committed 5 months ago

[Bugfix][MoE] Restore routed output unpadding before shared expert add (#45707)

Netanel Haber committed 5 months ago

[Quant] Support modelopt_mixed on Ampere (SM80/SM86) (#45306)

Mike G committed 5 months ago

[ROCm][CI] Gate incompatible HF references on Transformers v5 (#41532)

Andreas Karatzas committed 5 months ago

[ZenCPU] Add zencpu Platform Runtime Logging and Docs (#42726)

Lalithnarayan C committed 5 months ago

[Refactor] Remove `Fp8OnlineLinearMethod` as scheduled (#45463)

Wentao Ye committed 5 months ago

[KV Connector][Mooncake] Pipeline-parallel support for PD-disaggregated serving with Mooncake connector (#44528)

Hank Han committed 5 months ago

[MM][Perf][CG] Support dual-path ViT full CUDA graph for DeepSeek-OCR (#43586)

Shanshan Shen committed 5 months ago