Wes Johnson

skaman5

·

thewesjohnson

AI & ML interests

Observability, Interpretability, Capability

Recent Activity

upvoted an article 1 day ago

Profiling in PyTorch (Part 3): Attention is all you profile

liked a model about 1 month ago

JustinAngel/workshop-v1-pretraining

new activity about 2 months ago

poolside/Laguna-XS.2:Laguna architecture not yet supported by local Mac inference runtimes (llama.cpp, mlx-lm, LM Studio, Ollama)

View all activity

Organizations

None yet

New activity in poolside/Laguna-XS.2 about 2 months ago

Laguna architecture not yet supported by local Mac inference runtimes (llama.cpp, mlx-lm, LM Studio, Ollama)

#7 opened 2 months ago by

New activity in Qwen/Qwen3.5-9B 2 months ago

MTP provides no throughput improvement on Apple Silicon Metal (llama.cpp b9330) — net loss at every configuration

#56 opened 2 months ago by

New activity in mlx-community/Laguna-XS.2-4bit 2 months ago

Unable to load with mlx-lm 0.31.3 — architecture not recognized

#1 opened 2 months ago by

New activity in huggingchat/chat-ui about 1 year ago

Unusable Hugging Chat - httpError code 405 with content: POST method not allowed - when attempting to sign in.

#734 opened about 1 year ago by

Unusable Hugging Chat - httpError code 405 with content: POST method not allowed - when attempting to sign in.

#734 opened about 1 year ago by

Unusable Hugging Chat - httpError code 405 with content: POST method not allowed - when attempting to sign in.

#734 opened about 1 year ago by