[Rust Frontend] Reduce copy in auxiliary frame resolution (#54148)

Bugen Zhao committed about 2 months ago

[XPU]bump up vllm_xpu_kernels to 0.1.14.1 (#54203)

Xinyu Chen committed about 2 months ago

[Bugfix] Restore multimodal support on the plain "vllm" throughput backend (#52168)

Michał Ganczarenko committed about 2 months ago

[ROCm][CI] Warm up the RLHF dev server before the pause/resume timing checks (#53594)

stefankoncarevic committed about 2 months ago

[Bugfix][CI/Build] Fail closed when selected precompiled CUDA variant is unavailable (#52545)

Jung Jiyu committed about 2 months ago

[Kimi-K3][Bugfix] Fix low-latency GEMM fallback initialization (#54167)

Thien Tran committed about 2 months ago

[ROCm][CI] Keep startup profiling from aborting when free memory grows (#53591)

stefankoncarevic committed about 2 months ago

[Test] Fix mock_current_vllm_config missing kernel_config in test_dflash2 (#54132)

Qiming Zhang committed about 2 months ago

[CPU][MLA] Fix prefill backend selection so MLA runs end-to-end on CPU (#51471)

maobaolong committed about 2 months ago

Count store offers, not lookups, for CPU offload store_threshold (#52227)

Oxana Korzh committed about 2 months ago

[Bugfix][KV Cache] Prevent negative external block allocation (#52707)

haic0 committed about 2 months ago

[Bugfix] Allocate packed outputs in fused_q_kv_rmsnorm so q_b_proj keeps its low-latency GEMM path at decode (#53109)

Roy Wang committed about 2 months ago

Remove wrongly added e2e test (#54099)

Elvir Crnčević committed about 2 months ago

[Misc] Separate adaptive verification config validation (#54108)

Nick Hill committed about 2 months ago

[Bugfix] Remove race in fused groupwise RMSNorm quantization (#54111)

Misha Goin committed about 2 months ago

[Kimi-K3] Merge MLA gate into QKV-A projection (#54015)

Thien Tran committed about 2 months ago

fix(build): correct preprocessor guard for GDN decode to fix Ampere c… (#52743)

prakharPant committed about 2 months ago

[Bugfix] Revert renderer warmup overlap to avoid fork deadlock (#54023)

Kevin H. Luu committed about 2 months ago

[Rust Frontend][gRPC] Enforce LoRA path validation across transports (#53756)

Connor Carpenter committed about 2 months ago

[Bugfix][Model] Fix K3 DSpark config for 96-head drafts (#54005)

qizixi committed about 2 months ago