---
license: mit
---

llama.cpp Pull Request: https://github.com/ggml-org/llama.cpp/pull/22105

DFlash Drafter: https://huggingface.co/z-lab/Qwen3.6-35B-A3B-DFlash

Steps (follow the PR)
1) `git clone -b dflash https://github.com/ruixiang63/llama.cpp`

2) download draft model from https://huggingface.co/z-lab/Qwen3.6-35B-A3B-DFlash/

3) download tokenizer from https://huggingface.co/Qwen/Qwen3.6-35B-A3B

4) convert draft model to gguf
```python convert_hf_to_gguf.py ../Qwen3.6-35B-A3B-DFlash --outtype bf16 --target-model-dir ../Qwen3.6-35B-A3B --outfile ../Qwen3.6-35B-A3B-DFlash/Qwen3.6-35B-A3B-DFlash-bf16.gguf```

5) Build llama.cpp
- CUDA
```bash
cmake -B build -DGGML_CUDA=ON

cmake --build build --config Release -j
```

- VULKAN
```bash
cmake -B build -DGGML_VULKAN=ON

cmake --build build --config Release -j
```

6) Run DFlash speculative decoding

```bash
# thinking off: set LLAMA_SPEC_NO_THINK=1
# Omit it to test thinking-mode behavior
export LLAMA_SPEC_NO_THINK=1

for prompt in \
    "Write a quicksort algorithm in Python. Write code only." \
    "Explain the Pythagorean theorem" \
    "Plan a 1 day trip to DC"; do
  echo "=== Prompt: $prompt ==="
  ./build/bin/llama-speculative-simple \
    -m  "${TARGET_MODEL_GGUF}" \
    -md "${DFLASH_MODEL_GGUF}" \
    --dflash -p "$prompt" -n 256 \
    --draft-max 16 \
    -cd 512 -c 1024 \
    --temp 0 --top-k 1 --seed 42 \
    -ngl 99 -ngld 99
done
```

---

## Tests and Investigations

# 2026-04-19:
Rebase dflash feature onto latest master
```bash
git clone -b master https://github.com/ggml-org/llama.cpp
git remote add ruixiang63 https://github.com/ruixiang63/llama.cpp
git fetch ruixiang63
git checkout -b dflash-test origin/master
git merge ruixiang63/dflash --no-edit
```

Then solve conflicts manually
- gguf-py/gguf/constants.py
- src/CMakeLists.txt
- src/llama-arch.cpp
- src/llama-hparams.h
- src/llama-model.cpp

Notes
- src/CMakeLists.txt
Use glob to collect src/models sources: https://github.com/ggml-org/llama.cpp/pull/22005/changes

- src/llama-arch.cpp
remove per-arch tensor name lists: https://github.com/ggml-org/llama.cpp/pull/21531/changes

- src/llama-model.cpp
Refactor bias tensor variable names: https://github.com/ggml-org/llama.cpp/pull/22079/changes#diff-36e262e316ec1404e29880eb8b8ce4660ac584f0d0434710efc48a66497bdb59

from: 
```cpp
layer.bq = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "bias", i), {n_embd_head_k * n_head}, TENSOR_NOT_REQUIRED);
layer.bk = create_tensor(tn(LLM_TENSOR_ATTN_K,   "bias", i), {n_embd_k_gqa},          TENSOR_NOT_REQUIRED);
layer.bv = create_tensor(tn(LLM_TENSOR_ATTN_V,   "bias", i), {n_embd_v_gqa},          TENSOR_NOT_REQUIRED);
layer.bo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd},                TENSOR_NOT_REQUIRED);
```

to: 
```cpp
layer.wq_b = create_tensor(tn(LLM_TENSOR_ATTN_Q,   "bias", i), {n_embd_head_k * n_head}, TENSOR_NOT_REQUIRED);
layer.wk_b = create_tensor(tn(LLM_TENSOR_ATTN_K,   "bias", i), {n_embd_k_gqa},          TENSOR_NOT_REQUIRED);
layer.wv_b = create_tensor(tn(LLM_TENSOR_ATTN_V,   "bias", i), {n_embd_v_gqa},          TENSOR_NOT_REQUIRED);
layer.wo_b = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "bias", i), {n_embd},                TENSOR_NOT_REQUIRED);
```

- src/models/dflash.cpp follows the same

layer.bq -> layer.wq_b

layer.bk -> layer.wk_b

layer.bv -> layer.wv_b

layer.bo -> layer.wo_b

- src/models/eagle3.cpp:134:
support NVFP4 tensors for Gemma4: https://github.com/ggml-org/llama.cpp/pull/21971/changes#diff-9be9eea14f4aefce7375482c05968900192634e88e92ac263cedb955a64ad7feR2099

```cpp
        cur = build_attn(inp_attn,
                model.layers[il].wo, NULL, NULL, // 3rd tensor parameter (wo_s)
                Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
```

# 2026-04-20:
Support for Qwen3.5/3.6 MoE and notes
- https://github.com/ggml-org/llama.cpp/discussions/21569#discussioncomment-16624433

- https://github.com/ggml-org/llama.cpp/pull/22105/changes/d1d2c81caccc748eaaff32b6b7823bad090fd1dd

Z Lab's new benchmark
- https://huggingface.co/z-lab/Qwen3.6-35B-A3B-DFlash/commit/82252400cd9baebdfa5730b0aa809e10db5dba12

# 2026-04-22: 
Re-uploaded gguf based on new drafter https://huggingface.co/z-lab/Qwen3.6-35B-A3B-DFlash/commit/31977fbe13a86e8b961774f773058175676d89b8


# Issues and Solutions

/src/models/dflash.cpp:39: GGML_ASSERT(model.target_tok_embd != nullptr && "DFlash decoder requires target model's tok_embd") failed

check if `--dflash` param is added to the `llama-speculative-simple` test