Repository navigation
Description
Filed while resuming the Zyphra lane (~/briefs/T1BP-ZYPHRA-STATE.md, entry 2026-11-03 18:5x). This lane hit it converting the
Zyphra originals and worked around it in a throwaway checkout; the pin itself was left untouched and the finding never got a
tracker. It is one argparse block, and it breaks every conversion from the pin, not just dspark ones.
Where
third_party/llama.cpp pin d8bd0ff6052a3cc15b5f83d8d0625aac5b644404, which is also fork
1bit-MONSTER/llama.cpp branch 1bit/hrx-vulkan-patched HEAD — so a fresh clone at the pin behaves the same way.
Fix PR (fork): 1bit/convert-dspark-flag.
Root cause
convert_hf_to_gguf.py main():
if args.dspark: # :261 in the pinparse_args() registers --mtp, --no-mtp, --mistral-format, --fuse-gate-up-exps, --fp8-as-q8,
--sentence-transformers-dense-modules, --target-model-dir — and not --dspark. parse_args() therefore returns a
Namespace with no such attribute and main() raises before any model work: every model, every outtype, not only dspark ones.
The flag is otherwise a real, documented feature of this fork: src/models/deepseek41.cpp:226 tells the user to run
convert_hf_to_gguf.py --dspark, and conversion/deepseek41.py:301 implements DeepseekV41DSparkModel for exactly that flag.
Reproducer (before)
cd ~/cache/llama-pin-d8bd0ff6 # worktree at the pin, pristine convert_hf_to_gguf.py
PYTHONPATH=$PWD/gguf-py ~/venvs/d3ref/bin/python convert_hf_to_gguf.py \
~/models/zyphra-orig/ZR1-1.5B@6108a26d0cd7 --outtype bf16 --outfile /tmp/repro.gguf
INFO:hf-to-gguf:Loading model: ZR1-1.5B@6108a26d0cd7
INFO:hf-to-gguf:Model architecture: Qwen2ForCausalLM
Traceback (most recent call last):
File ".../convert_hf_to_gguf.py", line 307, in <module>
main()
File ".../convert_hf_to_gguf.py", line 261, in main
if args.dspark:
^^^^^^^^^^^
AttributeError: 'Namespace' object has no attribute 'dspark'
After (fork PR 1bit/convert-dspark-flag, +4 lines: one argparse block, nothing else)
| check | result |
|---|---|
convert_hf_to_gguf.py --help |
lists [--dspark] and its help line |
--dspark on a non-Deepseek model (ZR1-1.5B, Qwen2ForCausalLM) |
ERROR:hf-to-gguf:--dspark is only supported for DeepseekV4ForCausalLM and DeepseekV41ForCausalLM, exit 1 — the guard that was unreachable now runs |
full BF16 conversion of Zyphra/ZR1-1.5B@6108a26d0cd7 from the pin, patched |
completes: 3,560,417,696 B, sha256 d817473c0e56d2389fb5b0dc633ca33bdc7ec0d82448c318283800c0728744f3 |
| same conversion from the same originals, unpatched but with the same 4 lines applied in a local workaround (the reference this lane measured its whole quality table against) | byte-identical — same size, same sha256 d817473c… |
So for every non-dspark conversion the change is inert (same bytes out) and the dspark path stops being unreachable. Run was
~/lb/thermal-run.sh (4 cores, nice 19), 86 s wall for the 1.5B model.
Second half — same file, still broken, deliberately not in this PR
--dspark on a V4 (non-4.1) checkpoint does from conversion.deepseek import DeepseekV4DSparkModel, and
conversion/deepseek.py defines no such class (it has DeepseekModel, DeepseekV2Model, DeepseekV32Model,
DeepseekV4Model only) although both conversion/__init__.py and main() name it. So after this fix the V4.1 drafter path
works and the V4 one raises ImportError. Building it needs the checkpoint to test against (DeepSeek-V4-Flash-DSpark,
217 GiB-class family) — that is a DeepSeek V4.x conversion job, not an argparse one, so it is named here rather than guessed at.
Why it is worth an issue rather than a note in one lane's state file
Anything that converts from the pin dies on the first line of real work. This lane's artifacts and the other convert lanes'
were all produced with the same uncommitted local workaround, so nothing on disk is wrong — but a reader who clones the pin
and follows docs/ gets an AttributeError with no hint, and the flag the runtime error message tells them to pass does not exist.
Activity
bong-water-water-bong commentedon Nov 4, 2026
Fix PR (fork): 1bit-MONSTER/llama.cpp#187 — branch
1bit/convert-dspark-flag, head661382ba8ac5(verified withls-remote), base1bit/hrx-vulkan-patched, i.e. the exact commit the pin points at (d8bd0ff6is that branch's HEAD). +4 lines inparse_args(), nothing else. Not merged (owner merges), and it lands in the engine only whenthird_party/llama.cppis bumped to a commit containing it — this issue is the tracker for that bump.bong-water-water-bong commentedon Nov 4, 2026
Provenance, from the pi-prs lane's independent find: the missing block is upstream's own —
ggml-org/llama.cpp3581ba0cf"convert: add option to create separate dspark GGUF (#26452)" addsparser.add_argument("--dspark", action="store_true", help="Export only the DeepSeek-V4 DSpark draft tensors as a separate GGUF."). Our branch hasmain()'s caller (:261) and none of the flag, so the fix restores it verbatim.PR head updated to
fb176b5cdfc0fec87ffa37dc2a55bf8345872a26(help text is now upstream's wording). Duplicate disclosed: pi-prs pushed1bit/convert-dspark-arg(44b73c31) for the same four lines minutes later; I asked them to drop it, #187 is the single PR.bong-water-water-bong commentedon Nov 4, 2026
Final PR head:
9ee6a198497afd1a9ff80c07e21597de6958f6bc(the previous force-push had missed the working-tree change, sofb176b5still carried my own help text; corrected and re-verified against the pushed blob through the contents API). Branch content now equals upstream3581ba0cf's block verbatim.bong-water-water-bong commentedon Nov 4, 2026
Fork #187 is the fix and it is reviewed: the pin reads
args.dsparkatconvert_hf_to_gguf.py:261and registers no--dsparkargument, soargparseraisesAttributeErroron every conversion; #187 adds the registration at:156. It does not, however, carry upstream3581ba0cf's V4 class: on1bit/hrx-vulkan-patched,conversion/deepseek.pyhas noDeepseekV4DSparkModel(norconversion/qwen.pyaQwen3DSparkModel, thoughconversion/__init__.py:61lists both), so--dspark+DeepseekV4ForCausalLMwould still fail withImportError— the DeepSeek-V4.1 path is the one that becomes usable. Details and the branch audit are in the #187 review.registry: record the llama.cpp pin the bump moves to (engine #961)
Bump HRX: llama.cpp a5c32fbf8b (fork tip: the converter registers --d…