Commit Graph
6 Commits
Author SHA1 Message Date
antirez e68bcc8fab Package Qwen with original BF16 n-grams 2026-09-14 13:00:36 +02:00
ccea768827 Add Qwen3.8 Flash Next model support
Implement qwen4exp loading, 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 Exclude superseded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>
2026-09-13 14:57:29 +02:00
antirez 5da32061ba Merge GLM 5.3 SSD streaming and full checkpoint support
# Conflicts:
#	ds4.c
#	tests/test_glm53_kda.c
2026-08-31 13:25:05 +02:00
Salvatore Sanfilippo dcc70b41ef Generalize GLM quantization for full checkpoints 2026-08-31 03:33:22 -07:00
Salvatore Sanfilippo 10badf696c Quantize GLM 5.3 Q4 dense weights to Q8 2026-08-30 15:19:00 +02:00
antirez 147109a3cc Add GLM 5.3 Flash inference
Implement GLM 5.3 Q2 and Q4 inference across Metal and CUDA, including tensor parallelism, RDMA, batching, MTP, snapshots, SSD streaming, and GLM 5.2 shared-path improvements.

Add quantization and validation tools, official quality fixtures, model downloads, regression coverage, release QA, and user documentation.
2026-08-28 23:26:29 +02:00