Dwarf Star Support for Qwen3.8 Flash Next

Merged

Merged

Conversation #

Contributor Author

| Q4_K imatrix model for testing is here |

ivanfioravanti

force-pushedthe qwen3.8-flash-next branch from

to

ecf1da3

236cb2a Compare

September 6, 2026 10:33

This was referenced Sep 6, 2026

evandhoffmanadded a commit to evanwtf/local-llm that referenced this pull request

Sep 6, 2026

ivanfioravantimarked this pull request as draft

September 6, 2026 22:22

Contributor Author

| Finalizing Vision, Q2 and tools after rebase. |

ivanfioravanti

force-pushedthe qwen3.8-flash-next branch from

to

8f7c4fa

ffd85d4 Compare

September 6, 2026 23:11

ivanfioravantimarked this pull request as ready for review

September 6, 2026 23:18

evandhoffmanadded a commit to evanwtf/local-llm that referenced this pull request

Sep 7, 2026

evandhoffmanadded a commit to evanwtf/local-llm that referenced this pull request

Sep 8, 2026

This was referenced Sep 11, 2026

ivanfioravanti

force-pushedthe qwen3.8-flash-next branch from

to

ff4f0ff

3030554 Compare

September 12, 2026 23:32

| @ivanfioravanti Quick heads-up: the Q4_1 encoder froma0b1658 appears to have been dropped inb020c9f and the squashed3030554 , whileqwen4_pack.py still uses it for the PLE sidecar. The current native quantizer marks Q4_1 unsupported. The original implementation likely just needs to be restored before upstreaming. |

Contributor Author

| You rock! Gonna fix this! |

ivanfioravanti

force-pushedthe qwen3.8-flash-next branch 3 times, most recently from

to

d8ba365

cf5f223 Compare

September 13, 2026 09:21

Implement qwen4exp , tokenizer and chat formatting, PLE sidecars,
Metal text and vision graphs, built-in MTP, and recurrent KV persistence.
Integrate the CLI, agent, server, download targets, and conversion tools.

Preserve the native Q4_1 encoder, Q4_K accumulation guard, and shared
quantizer build target. Keep exact-MTP rewind and vision-cache row-width
fixes. Persist valid logits and recurrent state at completed prefill chunks,
and reuse Qwen text-answer history when tools clients omit reasoning.
Retain exact reasoning replay and test continued checkpoints, cancellation,
cache eviction, and restart reuse with and without reasoning_content. Include
reproducible charts and measurements comparing throughput before and after
the checkpoint fixes on M3 Ultra.

Add Qwen trunk steering and prompt activation capture, including GDN layers.
Keep the MTP predictor outside the 48-row bank and preserve prompt dumps
through one-token prefill tails and multi-row speculative verification.
Recover Chrome target creation and retain its last page target. Preserve
full agent transcripts in stripped-session format when KV no longer fits,
while retaining the newer automatic compaction and continuation logic.
Add steering/MTP/capture, Chrome CDP recovery, and full-session save/reload
regressions. Adapt the intended changes from fork PRs #13 and #7.

Reconcile with antirez main bd66c40, preserving DeepSeek v4.1 model IDs,
tool syntax, session state, and Metal kernel dispatch. Exclude superseded
engine code and prototypes.

Co-authored-by: Andreas Parusel <aparuael@7170c824-6152-4cf1-985e-9503832ce673.fritz.box>
Co-authored-by: david <contact@davidberard.fr>
Co-authored-by: Michael Kuebbeler <cropduster@users.noreply.github.com>
Co-authored-by: Ogilthorp3 <bertrand@nepveu.name>
Co-authored-by: anemll <realanemll@gmail.com>

ivanfioravanti

force-pushedthe qwen3.8-flash-next branch from

to

3989205

ccea768 Compare

September 13, 2026 13:05

  This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.

Learn more about bidirectional Unicode characters Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.

source & further reading

github.com — original article OpenCode Mentor: An anti-vibecoding, programming mentor configuration Show HN: Interakt – open-source self-hosted search and AI chat for your website Cortex: An open-source L1 memory and state layer for autonomous AI agents