[Doc] Add Qwen2.5 models to batch invariance tested models (#33016)

zhanqiuhu committed 10 months ago

[BugFix] Add env variable to control PDL in LoRA (#32836)

Jee Jee Li committed 10 months ago

[Bugfix] fix encoder cache hang in Qwen3VL (#32684)

JJJYmmm committed 10 months ago

[Docs] Fix Apple silicon include path in CPU installation docs (#32977)

7. Sun committed 10 months ago

[Perf][Kernel] Optimize FP4 quantization kernels (SM100F) (#32520)

Roberto L. Castro committed 10 months ago

[DOC] [ROCm] Update doc for v0.14.1 (#32998)

TJian committed 10 months ago

[Feature] add session based streaming input support to v1 (#28973)

Joshua Deng committed 10 months ago

Using max_loras + 1 to construct grid in fused_moe_lora (#32277)

yugong333 committed 10 months ago

[CPU] Improve CPU Docker build (#30953)

Maryam Tahhan committed 10 months ago

[CPU Backend][BugFix] Fix failing Darwin pipelines (#33002)

Fadi Arafeh committed 10 months ago

[Tests] Replace flaky sleep with polling in test_background_cancel (#32986)

7. Sun committed 10 months ago

[MLA] Fuse cat and qaunt for fp8 kv-cache (#32950)

Lucas Wilkinson committed 10 months ago

Update CPU doc according to feedback (#32963)

Louie Tsai committed 10 months ago

[Bugfix]: resolve torch.compile cache conflict between mm_encoder_tp_modes (#32842)

Hiroken. committed 10 months ago

[EncoderCacheManager] Remove unnecessary copy (#32800)

Lukas Geiger committed 10 months ago

feat: Complete LoRA support for MiniMaxM2 Fixes #32736 (#32763)

david guan committed 10 months ago

[Models]: Make Multimodal config implicit in ViT implementation (#31972)

Isotr0py committed 10 months ago

[Bugfix] Fix E2E latency calculation and add warmup support in mm_processor benchmark (#32646)

Hiroken. committed 10 months ago

[Perf] Cache exc.errors() result in validation exception handler (#32984)

7. Sun committed 10 months ago

[UX] Deduplicate sampling parameter startup logs (#32953)

Cyrus Leung committed 10 months ago