[BugFix] Scope divergent hybrid cache hits to capable connectors (#50344)

Yifan Qiao committed 3 months ago

[CI] fix docs on `main` (#51539)

Harry Mellor committed 3 months ago

[K3] Allow tpu to import kimi_k3.common (#51529)

Jeff (Junze) Ma committed 3 months ago

[KV Offload] Emit self-describing events for partial recurrent blocks (#51243)

Chauncey committed 3 months ago

[ROCm][CI] Reuse equivalent ROCm CI images (#48646)

Andreas Karatzas committed 3 months ago

Bump Flashinfer version to 0.6.16.post3 (#50892)

Wei Zhao committed 3 months ago

[Bugfix][KV Offload] Handle chunked local attention in offloading scheduler (#51161)

Almog Tavor committed 3 months ago

[KV Offload] Fix failed-load livelock by marking the lookup verdict as a miss (#49328)

Robbie J committed 3 months ago

[Bugfix][Build] Patch stable string memleak fix from 2.14 for 2.13 (#51185)

Jane (Yuan) Xu committed 3 months ago

[Migration] Migrate bitsandbytes support to OOT plugin (#43529)

Isotr0py committed 3 months ago

[V1][Metrics] Preserve prefix-cache stats on zero-output steps (#48668)

Rishi Puri committed 3 months ago

[Build] Upgrade runtime image to Ubuntu 24.04, pick up rdma-core > 44 (#51058)

Tyler Michael Smith committed 3 months ago

[Test] Add ROCm AITER FP8 MLA prefill accuracy test (#51457)

Aarushi Jain committed 3 months ago

[Core] Make the GPU sync check thread-local and fix its suppressors (#51455)

Nick Hill committed 3 months ago

[Perf] Avoid some more unnecessary GPU<->CPU syncs (#51458)

Nick Hill committed 3 months ago

[Bugfix][MRV2] Reserve spec-decode lookahead blocks in V2 warmup (#51438)

Nick Hill committed 3 months ago

[Perf][Sparse MLA] Drop the atomic contention in the index remap (#50365)

Nick Hill committed 3 months ago

[Bugfix][Parser] Confirm reasoning end when an Inkling content block opens (#49876)

Vegetog committed 3 months ago

[Bugfix][Parser] Prevent Inkling block-end leakage with tools (#51391)

cherry77-cloud committed 3 months ago

[BugFix] Preserve divergent FA hits with external Mamba state (#51468)

Jeff (Junze) Ma committed 3 months ago