ENTITY
qwen35moe
qwen35moe
PulseAugur coverage of qwen35moe — every cluster mentioning qwen35moe across labs, papers, and developer communities, ranked by signal.
Total · 30d
2
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
0 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D
1 day(s) with sentiment data
RECENT · PAGE 1/1 · 2 TOTAL
-
llama.cpp b11477 optimizes tensor flag sharing across models
The llama.cpp project has released version b11477, which introduces optimizations for handling tensor flags across different models. This update centralizes the detection logic for trunk-only and MTP-only models into a …
-
llama.cpp now loads MTP tensors by default, increasing resource usage
The popular open-source inference engine llama.cpp has updated its default behavior to automatically load Multi Token Prediction (MTP) tensors. This change affects models that have MTP tensors baked in, such as GLM-5.2,…