chore(deps): bump flashinfer-python from 0.6.12 to 0.6.15.post1

[dependabot]

Bumps flashinfer-python from 0.6.12 to 0.6.15.post1.

Release notes

Sourced from flashinfer-python's releases.

Release v0.6.15.post1

Full Changelog: flashinfer-ai/flashinfer@v0.6.15...v0.6.15.post1

Release v0.6.15

Highlights

This release ships Expert Parallelism (moe_ep) in the default install and extends the TRTLLM-GEN MoE stack for large-model serving. It broadens Blackwell model coverage — Gemma 4 / MiniMax-M3 MoE on consumer / DGX-Spark SM12x, DeepSeek-class MLA decode on B300, and context-parallel GDN on SM120 — and adds Video Sparse Attention plus CUDA-graph-safe FP8 all-reduce fusion for distributed inference.

Unified MoE API with Expert Parallelism (Experimental API to try!)

FlashInfer's unified MoE compute API is now wired into expert parallelism. A new flashinfer.moe_ep.MoEEpLayer runs one MoE layer split across ranks as dispatch → per-expert grouped GEMM → combine, over pluggable transport (NCCL-EP via nccl.ep/nccl4py, and NIXL-EP). The expert GEMM reuses the unified flashinfer.fused_moe.MoELayer as a pure per-expert grouped GEMM — routing lives in dispatch/combine. moe_ep is part of the default install (CUDA 13+), with vLLM-facing APIs and checkpoint-safe MoE all-to-all graph VAs. This EP API is also the integration surface for MegaMoE kernels in upcoming releases — try it out and let us know how it works for you.

• #3686
• #3821
• #3813
• #3727
• #3591

Gemma 4 and MiniMax-M3 NVFP4 MoE now run on Blackwell SM12x

Gemma 4 and MiniMax-M3 NVFP4 MoE now run on Blackwell SM12x (consumer / DGX Spark), enabled by two new NVFP4 MoE activation functions — gelu_tanh and swiglu_oai — added to the SM12x MoE path.

• #3744
• #3737

TRTLLM-GEN MoE adds shared experts, DeepSeek-V4 routing, and low-latency FP8

TRTLLM-GEN MoE gains shared-expert fusion for FP8 paths, hash-based DeepSeek-V4 routing (hash_topk), and a fused FP8 blockwise megakernel that cuts latency for small batches (BS ≤ 8).

• #2625
• #3561
• #3424

Video Sparse Attention and DeepSeek MLA decode on Blackwell B300

Video Sparse Attention (VSA) is now integrated into the block-sparse attention API, bringing efficient long-context attention for video diffusion models to FlashInfer. DeepSeek-class MLA decode extends onto Blackwell B300 (SM103) with cluster-aware CUTLASS split_kv, and CuTe-DSL GQA decode adds sliding-window and attention-sink masking for newer attention variants.

• #3250
• #3888
• #3794

Linear attention: context-parallel GDN on SM120 and faster KDA decode

Gated delta-rule (GDN) linear attention adds SM120 context-parallel delta rule support, extending the CuTe-DSL GDN rewrite from 0.6.14 onto Blackwell SM120 prefill, alongside SM90 context-parallel prefill optimizations. KDA recurrent-decode kernels are also optimized for lower decode latency.

• #3659
• #3788
• #3766

Distributed comm: FP8 fusion and CUDA-graph checkpoint restore

... (truncated)

Commits

• de358e8 bump version to 0.6.15.post1
• 5eec7b1 Autotuner mem leak follow up 2 (#3970)
• 6356514 fix(fused_moe): avoid repeated runner setup in host dispatch (#4045)
• 8eccd0c bump version to 0.6.15
• 0b24eb5 bump version to 0.6.15rc4
• 0613344 fix(gemm): skip low-latency FP8 path for K-major m=32 on SM100 (#3953)
• 90d91a6 Update moe cubins to fix 2CTA hanging issue (#3973)
• a00d4c2 bump version to 0.6.15rc3
• 99540bb perf(attention): reuse TRT-LLM-gen counter buffers (#3949)
• d001f82 test(moe): align EP-offset tests and docs with global expert ids (gh #3547) (...
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!