EntrpiandClaude Fable 5
0f62c620e8
Vendors the Entrpi/ds4 fork's cuda/mmq module at its v0.5.1 state (llama.cpp mmq kernels pinned in cuda/mmq/VENDOR.md, MIT, plus the fork's ds4_mmq C ABI, D2R kernels and repack library; fused prefill pipeline portions carry Marco Palaferri's Portions-Copyright headers) and wires the RAW-layout tier only: dense Q8_0 GEMMs and the IQ2_XXS gate/up pair + Q2_K down routed-MoE pipeline at n_tok >= 2. The aligned-SoA / D2R / producer-quantized tiers and the weight server are deliberately not wired (they need the repack artifact pipeline). Decode (n_tok == 1) is untouched. mmq changes FP32 reduction order vs the cublas+dequant pipeline, so prefill logits drift at ULP scale: gated on quality mode off, DS4_CUDA_MMQ=0 restores legacy dispatch. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011CsqQzZEeuz9biUSEkGm8b
5 lines
104 B
C
5 lines
104 B
C
// SPDX-License-Identifier: MIT
|
|
// Thin redirect - see ggml.h.
|
|
#pragma once
|
|
#include "ds4_ggml_stubs.h"
|