[MM][CG] Support ViT CUDA Graph for Gemma-4 (#46837)

anthonsu committed 3 months ago

[Build] Fix for DeepEP manylinux pidfd sycall usage (#49814)

Tyler Michael Smith committed 3 months ago

[CI] Stabilize Pooling Rerank Equivalence Test (#49822)

Taneem Ibrahim committed 3 months ago

[Bugfix] Wait for the linear bias before layerwise online processing (#49805)

Harry Mellor committed 3 months ago

[Model] Add VaultGemma via Transformers modeling backend (#49803)

Harry Mellor committed 3 months ago

[Perf] Fix moe `reduce_scatter` perf regression by removing additional comm, 5% E2E throughput gain back. (#48763)

Wentao Ye committed 3 months ago

Mergify message not on cancelled (#45117)

Harry Mellor committed 3 months ago

[Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments (#44428)

fangyuchu committed 3 months ago

[BugFix] Increase the max supported duration for MOSS-TD (#49403)

Canlin Guo committed 3 months ago

[Docs] Use `gen-files` for generated docs content (#49587)

Harry Mellor committed 3 months ago

[Bugfix][MiniMax-M3] Fix token-major top-k buffer handling in Triton … (#49149)

rongfu.leng committed 3 months ago

[Bugfix][Tool Parser] Fix dropped streaming arguments in Jamba and InternLM2 parsers (#48852)

mosya415 committed 3 months ago

[CI] Stop flaky test from downloading model every time (#49800)

Harry Mellor committed 3 months ago

feat[vLLM × v5]: Add audio support for the Transformers backend (#39330)

Harshal Janjani committed 3 months ago

Make bare `hugging_face` imports forbidden (#49726)

Harry Mellor committed 3 months ago

[Bugfix][CI] Fix stale Mooncake lookup expectation broken by a merge race (#49802)

Harry Mellor committed 3 months ago

[Core] Keep attention backends eligible for text-only serving of prefix-LM models (#48796)

Tri Vo committed 3 months ago

[Model] Remove Ouro (#49786)

Harry Mellor committed 3 months ago

[Perf][V1] Skip LRU hash-split in free_blocks when prefix caching is off (#48017)

Agata Dobrzyniewicz committed 3 months ago

[Docs] Fix confusing docstring indentation in nemotron_h.py (#49781)

Johnny-Liou committed 3 months ago