Joe Rocca's picture

Joe Rocca PRO

rocca

·

AI & ML interests

None yet

Recent Activity

liked a model about 6 hours ago

nvidia/DeepSeek-V3.1-NVFP4

liked a model 1 day ago

lightx2v/Hy1.5-Distill-Models

liked a model 7 days ago

ISTA-DASLab/DeepSeek-V3-0324-GPTQ-4b-128g-experts

View all activity

Organizations

New activity in amd/DeepSeek-R1-0528-MXFP4-ASQ 28 days ago

Minimal working setup for SGLang (and vLLM?)

#2 opened 28 days ago by

New activity in rocca/chroma-nunchaku-test 4 months ago

Which model to be loaded?

#3 opened 4 months ago by

New activity in rocca/chroma-nunchaku-test 5 months ago

FP4 quantization, INT4 crash on RTX 50XX

#2 opened 6 months ago by

Any chance of creating a v30 version to hold over until real support?

#1 opened 6 months ago by

New activity in QuixiAI/DeepSeek-V3-0324-AWQ 6 months ago

Does FlashMLA support kv cache fp8 dtype and how to enable FlashMLA ?

#6 opened 8 months ago by

New activity in lodestones/Chroma 8 months ago

Diffusers Roadmap?

#5 opened 9 months ago by

New activity in ibm-ai-platform/llama-13b-accelerator over 1 year ago

70B model?

#1 opened over 1 year ago by

New activity in MaziyarPanahi/miqu-1-70b-sf-GPTQ over 1 year ago

vllm can not inter this model (other 70b gptq model are ok)

#1 opened almost 2 years ago by

New activity in text-generation-inference/commandrplus-medusa over 1 year ago

Is `--speculate` needed for Medusa in TGI?

#1 opened over 1 year ago by

New activity in TheBloke/goliath-120b-GPTQ almost 2 years ago

Double-hyphen in "gptq-3bit--1g-actorder_True" branch name is invalid according to TGI

#1 opened almost 2 years ago by

New activity in rocca/lyra-v2-soundstream about 3 years ago

Conversion to ONNX

#1 opened about 3 years ago by

New activity in rocca/rwkv-4-pile-web about 3 years ago

Delete the outdated rwkv-4-pile-430m-webgl.onnx

#4 opened about 3 years ago by

Upload rwkv-4-pile-430m-webgl.onnx

#3 opened about 3 years ago by

New activity in rocca/rwkv-4-pile-web over 3 years ago

Upload rwkv-4-pile-430m-webgl.onnx

#2 opened over 3 years ago by

Upload rwkv-4-pile-169m-webgl.onnx

#1 opened over 3 years ago by

New activity in rocca/openai-clip-js over 3 years ago

This is really exciting

#1 opened over 3 years ago by