Update GLM-4.5 Doc transformers version (#25830)

Yuxuan Zhang committed about 1 year ago

Fix random dataset mismatched token length with config. (#24937)

weiliang committed about 1 year ago

[VLM] Update Qwen3-VL max_num_video_tokens calculation for configurable video profiling (#25557)

Isotr0py committed about 1 year ago

[Bugfix] Fix Qwen3-VL regression from #24982 (#25814)

Roger Wang committed about 1 year ago

[MM] Optimize memory profiling for scattered multimodal embeddings (#25810)

Roger Wang committed about 1 year ago

[Bugfix][NIXL] Fix Async Scheduler timeout issue (#25808)

Nicolò Lucchesi committed about 1 year ago

[Core] GC Debug callback (#24829)

Jialin Ouyang committed about 1 year ago

[Bug]: Set LD_LIBRARY_PATH to include the 'standard' CUDA location (#25766)

Clayton Coleman committed about 1 year ago

[torch.compile]: Add VLLM_DEBUG_DUMP_PATH environment variable (#25651)

Jiangyun Zhu committed about 1 year ago

[Core] Refactor self.model() to call a helper for subclassing. (#25084)

Patrick C. Toulme committed about 1 year ago

[env] default nixl side port conflicts with kv-event zmq port (#25056)

Peter Pan committed about 1 year ago

[docs] transcriptions API audio upload (#25446)

yyzxw committed about 1 year ago

[Bugfix][WideEP] Apply TP Attn + EP MoE fix to other models (#24982)

Tyler Michael Smith committed about 1 year ago

[Bugfix] Fix triton import precommit failure (#25803)

Tyler Michael Smith committed about 1 year ago

Fix GPTQ model loading in Transformers backend (#25770)

Harry Mellor committed about 1 year ago

Add filtering for chat template kwargs (#25794)

Russell Bryant committed about 1 year ago

Validate API tokens in constant time (#25781)

Russell Bryant committed about 1 year ago

[Bugfix] Merge MM embeddings by index instead of token IDs (#16229)

Cyrus Leung committed about 1 year ago

[Bugfix] Add missing `image_size` for phi4_multimodal (#25796)

Xiaohan Zou committed about 1 year ago

[Misc] Update openai client example file for multimodal (#25795)

Roger Wang committed about 1 year ago