[V1] Wrapper which plumbs request-level logits processors into vLLM batch-level logits processing (#23656)

afeldman-nm committed about 1 year ago

Upgrade xgrammar to 0.1.23 (#22988)

Russell Bryant committed about 1 year ago

Update release pipeline post PyTorch 2.8.0 update (#24073)

youkaichao committed about 1 year ago

[XPU] Fix the bug of LoRA logits on the XPU platform (#24081)

Chaojun Zhang committed about 1 year ago

[CI/Build] Disable SiluMul NVFP4 quant fusion tests (#24121)

Matthew Bonanni committed about 1 year ago

[Bug] R1 Accuracy: Fix `routed_scaling_factor` Double Mul Issue (#24119)

Wentao Ye committed about 1 year ago

[AMD][Kernel][Bugfix] Cast offsets tensor bn to tl.int64 to avoid GPU segfault (#23692)

rasmith committed about 1 year ago

[CI] Enable all hf transformers baselines in test_hybrid (#23936)

Thomas Parnell committed about 1 year ago

[Log] Only Print Profiler Results on Rank 0 (#23370)

Wentao Ye committed about 1 year ago

Fix weights loading for Apertus (#24100)

nathan committed about 1 year ago

[Metrics] Deprecate TPOT in favor of ITL (#24110)

Mark McLoughlin committed about 1 year ago

[Bugfix] Fix packed_factor missing attribute error (#23902)

Kyuyeun Kim committed about 1 year ago

Run ruff format on a few files. (#24075)

Chenheli Hua committed about 1 year ago

[Bugfix] Fix transform_config parsing in Compressed Tensors (#23945)

Kyle Sayers committed about 1 year ago

[Benchmark] Add support for local hf dataset path in benchmark (#23999)

Jiangyun Zhu committed about 1 year ago

[docs] add SYS_NICE cap & `security-opt` for docker/k8s (#24017)

Peter Pan committed about 1 year ago

[CI Failure] Skip failing nvfp4 silu test (#23959)

Michael Goin committed about 1 year ago

[Model] Classification models support logit_bias / sigmoid_normalize (#24031)

wang.yuqi committed about 1 year ago

[BugFix] Fix EXAONE4 rotary embeddings (#23918)

Kyungmin Lee committed about 1 year ago

[Gemma3n] Fix audio batching (#24052)

Nicolò Lucchesi committed about 1 year ago