[XPU][CI] fix hf runner (#52730)

Qiming Zhang committed 2 months ago

[MM] Keep more metadata tensors on CPU (#52827)

Nick Hill committed 2 months ago

[Bugfix][Benchmark] Check readiness before tokenizer init in rust vllm-bench (#51863)

Tyler Michael Smith committed 2 months ago

[XPU] upgrade requirements/test/xpu.txt (#52672)

Qiming Zhang committed 2 months ago

[Bugfix][XPU] Fix Mamba state pointer overflow (#48109)

Willow Lopez committed 2 months ago

[CPU] Add AMX-only high-performance MLA backend for DeepSeek V2/V3/R1 (#52616)

Li, Jiang committed 2 months ago

[XPU] Support EC connector KV Offloading on XPU (#49532)

Chaojun Zhang committed 2 months ago

[EPD] Allow KV consumers to omit MM embeddings (#52697)

liuzhenwei committed 2 months ago

[Elastic EP] Reduce eager-mode reconfiguration downtime (#51885)

Itay Alroy committed 2 months ago

[Bugfix][Elastic EP] Reject scale below the minimum data parallel size (#52702)

Itay Etelis committed 2 months ago

[CI][Bugfix] Complete DeepSeek-V4 FSE test fixture contract (#52842)

Kevin H. Luu committed 2 months ago

Revert DSv4 eager workspace reuse (#52836)

Woosuk Kwon committed 2 months ago

[Bugfix] Fix DeepSeek V4 mHC broadcast buffer for dummy load (#51368)

ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 committed 2 months ago

[Core] Make prefix-cache NONE_HASH deterministic by default (#51875)

Russell Bryant committed 2 months ago

[ROCm][CI] Gating more ROCm tests (#44969)

Andreas Karatzas committed 2 months ago

[CI][ROCm] Prevent Git maintenance races during shallow fetches (#52810)

Andreas Karatzas committed 2 months ago

[ROCm][CI] Add AMD CI Pull-Request Commands (#52822)

Andreas Karatzas committed 2 months ago

[nv] add pcp support in dsv3.2 (#52046)

Summer Yang committed 2 months ago

[Quantization] Remove the dead ocp_mx_scheme branch from moe_kernel_quantize_input (#52603)

xuebwang-amd committed 2 months ago

[ROCM][CI] Attention test speedup (#52763)

stefankoncarevic committed 2 months ago