[ROCm][Quantization] Add Quark W4A8 (INT4-FP8) MoE CI coverage (#48050)

amd-sourjya committed 3 months ago

[Docs] Fix broken anchor links in serving/pooling/MoE docs (#49654)

Euisuh Jeong committed 3 months ago

[ROCm][CI] Prepare AMD mirrors for regating (#49270)

Andreas Karatzas committed 3 months ago

[BugFix][LoRA] Skip marlin-backend gpt-oss LoRA tests on XPU (#49385)

Chaojun Zhang committed 3 months ago

[CI][PD] Add hybrid SSM P_TP>D_TP accuracy sweep entry (#49593)

Nicolò Lucchesi committed 3 months ago

[CI] Disable reasoning in Responses smoke test (#49511)

Andreas Karatzas committed 3 months ago

[ROCm][CI] Language Models tests tiny-mixtral with aiter fix (#49551)

music-dino committed 3 months ago

[Bugfix][KV cache] Support sparse-MLA targets with SWA drafts (#48776)

Michael Goin committed 3 months ago

[Bug] Fix batch invariance rms norm comparison (#49603)

Wentao Ye committed 3 months ago

[Bugfix] Restore structured output logger initialization (#49626)

Chang Guo committed 3 months ago

[Core] Update PyTorch to 2.13.0, torchvision to 0.28.0, triton to 3.7.1 (#48155)

Andrey Talman committed 3 months ago

[CI] Bump PyTorch Compilation Unit Tests timeout to 150 min (#49606)

Andrey Talman committed 3 months ago

[CI][Bugfix] Fix test isolation in block_int8/ptpc_fp8 MoE kernel tests (#49609)

Nick Hill committed 3 months ago

[CI] Isolate cudagraph tests in child processes (#49510)

Andreas Karatzas committed 3 months ago

[DSv4 Perf] Skip topk and router when not needed, 3.4% E2E TTFT improvement for Decode case (#49486)

Wentao Ye committed 3 months ago

[CI] Use explicit devices in quantization tests (#49512)

Andreas Karatzas committed 3 months ago

Revert "[MRV2] Always build attn metadata at capture time" (#49364) (#49451)

vllm-agent committed 3 months ago

[Bugfix][Structured Output][Spec Decode] Advance grammar across reasoning boundary (#44993)

yue.yu committed 3 months ago

Fix GPTQ quantized Qwen3.5 MTP weight loading with spec decode (#48816)

vllmellm committed 3 months ago

[Perf] Defer MM embeds loading off the event loop (#49477)

Guan-Ming Chiu committed 3 months ago