All pull requests

Pull requests

• docs: list the DiffusionGemma-26B-A4B-it image and add its serving recipe

  #259·yeahdongcn opened Sep 24, 2026Collaborator·

  ·
  1

• MUSA: route the Mamba2 SSD to FlashInfer for --mamba-backend flashinfer

  #257·yeahdongcn opened Sep 23, 2026Collaborator·

  ·

• fix(musa): keep FusedInputNorm identity check on CPU scalars

  #255·Elon-yf opened Sep 23, 2026·

  ·

• fix(series): make the patch series replayable with git am (+ regen + gate)

  #250·yeahdongcn opened Sep 21, 2026Collaborator·

  ·
  2

• MUSA: DiffusionGemma structured reads (port of upstream PR #57250)

  #249·yeahdongcn opened Sep 21, 2026Collaborator·

  ·
  2

• fix(musa): complete Mamba prefix-cache eviction handling

  #247·lllszzz opened Sep 21, 2026·

  ·

• build: move the MUSA stack to torch 2.11.0.post2 and torchada 0.1.89

  #240·yeahdongcn opened Sep 18, 2026Collaborator·

  ·

• MUSA: stack FlashInfer Mamba2 SSD on Nemotron

  #233·yeahdongcn opened Sep 12, 2026Collaborator·

  ·

• MUSA: add DFlash2 for Qwen3.8-27B adaptation patch

  #230·lllszzz opened Sep 10, 2026·

  ·

• [MUSA] Add vLLM-Omni 0.28.0 image target

  #220·yeahdongcn opened Sep 2, 2026Collaborator·

  ·

• [Model] Enable GLM-5.3-Flash on MUSA

  #209·lllszzz opened Aug 31, 2026·

  ·

• [Model] Enable Tencent Hy4-preview on MUSA (v0.28.0)

  #205·yeahdongcn opened Aug 29, 2026Collaborator·

  ·
  1

• perf(musa): select AOT and JIT tiles by active MP

  #202·yeahdongcn opened Aug 28, 2026Collaborator·

  ·
  6

• [Model] Enable Qwen3.8-Flash-Next on MUSA

  #200·Joey-gvwal opened Aug 27, 2026Collaborator·

  ·
  1

• MUSA: enable CAR-RMSNorm by default under contract

  #199·Elon-yf opened Aug 27, 2026·

  ·

• [Draft] feat(musa): unify RuntimePlan and add in-tree engine autotuning

  #185·yeahdongcn opened Aug 17, 2026Collaborator·

  ·
  18

• MUSA: switch Ubuntu 22.04 image to system Python 3.12

  #119·yeahdongcn opened Jul 24, 2026Collaborator·

  ·
  1