git
ask
hub
Privacy
Terms
Sign in with GitHub
tonyd2wild/glm5.2-2bit-2-dgx-spark--21.5tok-s
↗
Stars ·
31
Language ·
Python
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: tonyd2wild
Ask anything about this repo to start.
Walk me through the ten failure modes documented in this repo and how each was fixed.
Help me verify my model checkpoint has no missing shards using tools/tensor_audit.py from this repo.
Explain why this setup uses 2-bit quantization for experts but keeps attention in FP8.
Help me apply the patches in this repo to my own vLLM-Moet deployment.
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).