Code

History

Commits on main to patch10
  1. Three-tier hierarchy shipped: host 2-bit -> GPU 2-bit cache -> gate-filled FP4kacper-daftcode committed 4 months agocf02998
  2. Sync the shipped patch with worktree HEAD (base-cache miss-tolerance knob)kacper-daftcode committed 4 months ago1b1fd28
  3. 159B on one RTX 5090: host-resident 2-bit base with the GPU as an expert cachekacper-daftcode committed 4 months ago6da9beb
  4. Sync the shipped patch with HEAD (AFRAG default-on) + honest README claimskacper-daftcode committed 4 months ago68e38f6
  5. GLM-5.2-NVFP4 live on TP4 + MTP-under-PP: loader, runner fixes, first numberskacper-daftcode committed 4 months ago4747bf4
  6. Delta pool auto-sizing: VLLM_MOE_W2_DELTA_GB=auto sizes the FP4 pool from free VRAM after KV allocationkacper-daftcode committed 4 months agof445898
  7. Remove legacy v0.19 fork files (old patch, Dockerfile, BUILD.md, serve.sh); NOTICE -> v0.24.0 basekacper-daftcode committed 4 months ago3d845fe
  8. Confidence-gate driver re-integrated on v0.24 (patch now 20 files, +3.7k)kacper-daftcode committed 4 months ago04c52c9
  9. v0.24.0 port: rebase onto official vLLM, GLM-5.x prep, same-day A/B benchmarkskacper-daftcode committed 4 months ago406fe04
  10. vLLM-Moet: DeepSeek-V4-Flash on SM120 (Blackwell)Kacper committed 4 months ago9093a5c