[v1][Core] Clean up usages of `SpecializedManager` (#21407)

Zhou Fang committed over 1 year ago

[TPU][Bugfix] fix moe layer (#21340)

Chengji Yao committed over 1 year ago

[Bugfix][ROCm] Fix for warp_size uses on host (#21205)

Gregory Shtrasberg committed over 1 year ago

Deduplicate Transformers backend code using inheritance (#21461)

Harry Mellor committed over 1 year ago

Add think chunk (#21333)

Julien Denize committed over 1 year ago

[BugFix] Set CUDA_VISIBLE_DEVICES before spawning the subprocesses (#21211)

Yinghai Lu committed over 1 year ago

Dump input metadata on crash for async scheduling (#21258)

Woosuk Kwon committed over 1 year ago

[DP] Internal Load Balancing Per Node [`one-pod-per-node`] (#21238)

Robert Shaw committed over 1 year ago

[BugFix] Fix KVConnector TP worker aggregation (#21473)

Nick Hill committed over 1 year ago

[BugFix]: Batch generation from prompt_embeds fails for long prompts (#21390)

KazusatoOoko committed over 1 year ago

[Bugfix] Fix example disagg_example_p2p_nccl_xpyd.sh zombie process (#21437)

WeiQing Chen committed over 1 year ago

[Bugfix] Fix casing warning (#21468)

Matthew Bonanni committed over 1 year ago

[XPU][UT] increase intel xpu CI test scope (#21492)

Liangliang Ma committed over 1 year ago

[Misc] Add dummy maverick test to CI (#21324)

Ming Yang committed over 1 year ago

[Frontend] Set MAX_AUDIO_CLIP_FILESIZE_MB via env var instead of hardcoding (#21374)

deven-labovitch committed over 1 year ago

feat(gguf_loader): accept HF repo paths & URLs for GGUF (#20793)

Hardik Gupta committed over 1 year ago

[Core] Freeze gc during cuda graph capture to speed up init (#21146)

Michael Goin committed over 1 year ago

[V0 Deprecation] Remove Prompt Adapters (#20588)

Michael Goin committed over 1 year ago

[V1] Fix local chunked attention always disabled (#21419)

Yong Hoon Shin committed over 1 year ago

[Core] Add `reload_weights` RPC method (#20096)

22quinn committed over 1 year ago