All pull requests

Pull requests

• [Benchmark] Make sweep parameters configurable via CLI flags

  run-ci
  #536·arathi-hlab opened Oct 12, 2026Collaborator·

  ·

• GDN: split the fused kernel to align with CUDA; add verify kernels for speculative decoding

  #535·Xia-Weiwen opened Oct 12, 2026Collaborator·

  ·
  5

• Optimize MHA decode perf with 512 head_dim

  run-ci
  #534·gaopengff opened Oct 12, 2026Collaborator·

  ·
  2

• [XPU] SYCL port of the ngram-embedding kernels (LongCat-Flash)

  #532·desmond-intel opened Oct 9, 2026Contributor·

  ·
  3

• [Inkling] Optimize attention prologue prefill on XPU

  run-ci
  #531·yuankuns opened Oct 9, 2026Collaborator·

  ·
  2

• [Inkling] Optimize causal SConv prefill on XPU

  run-ci
  #530·yuankuns opened Oct 8, 2026Collaborator·

  ·
  4

• Add rmsnorm_heads_inplace: RMSNorm the leading heads of a packed row in place

  #529·jmunetong opened Oct 5, 2026Collaborator·

  ·
  4

• Add Inkling MoE gate top-k + logsigmoid renorm Triton kernel

  #528·jmunetong opened Oct 5, 2026Collaborator·

  ·
  1

• (WIP) multi device support

  #527·mkumargarg opened Oct 5, 2026Collaborator·

  ·

• To support bmm_fp8/bf16/fp16 kernel

  #519·mkumargarg opened Sep 28, 2026Collaborator·

  ·
  8

• Switch the build and CI environment from conda to uv

  #514·htzo opened Sep 24, 2026Collaborator·

  ·
  19

• [quant] add round_mode parameter in per_token_group_quant_8bit & per_token_group_quant_mxfp4

  #513·MeowMiaoJ opened Sep 24, 2026Contributor·

  ·

• [ci] Add workflow to test a prebuilt wheel on a given ref and Python version

  #511·arathi-hlab opened Sep 23, 2026Collaborator·

  ·
  2

• [XPU] Add the DeepSeek V4 expand_prefill_causally attention metadata op

  #505·unrahul opened Sep 21, 2026·

  ·
  1

• [XPU] Fuse QK into the fp8 paged MQA logits triton kernel

  #504·unrahul opened Sep 21, 2026·

  ·
  1

• perf(moe): fuse the W4A16 MoE prepare path at M==1

  run-ci
  #496·jmunetong opened Sep 17, 2026Collaborator·5 tasks done·

  ·
  11

• Align on Python 3.12 as the single supported interpreter

  #493·arathi-hlab opened Sep 16, 2026Collaborator·

  ·

• ci(xpu): add a CRI (Xe3P) build gate to PR CI

  #492·arathi-hlab opened Sep 16, 2026Collaborator·2 tasks done·

  ·
  1

• Xpu kernel upgrade to 1.0 for sglang-v0.5.19 rebase + Mamba-Hicache fix needed new new kernel

  #488·XiangKaren opened Sep 13, 2026·

  ·

• [MoE] Adopt Column-Major Layout B for Xe2 Grouped GEMM

  #484·CaoE opened Sep 10, 2026Collaborator·

  ·
  22

• [MoE] Optimize small-input preparation

  #483·CaoE opened Sep 10, 2026Collaborator·

  ·

• [MoE] Optimize MoE input preparation and adopt Column-Major Layout B for Grouped GEMM

  #482·CaoE opened Sep 9, 2026Collaborator·

  ·

• [Inkling] Add relative projection kernel

  run-ci
  #468·yuankuns opened Sep 2, 2026Collaborator·

  ·
  2

• CI: Update baseline.json (from PR #457)

  #463·MingxuZh opened Sep 1, 2026Collaborator·

  ·
  2

• CI: Update baseline.json (from PR #459)

  #460·MingxuZh opened Aug 31, 2026Collaborator·

  ·
  1