Will Reynolds

willowill5's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 about 1 year ago

OOM with vllm

#48 opened about 1 year ago by

willowill5

New activity in TheBloke/zephyr-7B-beta-AWQ over 1 year ago

vLLM out of memory

2

#2 opened over 1 year ago by

cfrancois7

New activity in TheBloke/zephyr-7B-alpha-AWQ over 1 year ago

OOM on RTX 3090 with vLLM

#1 opened over 1 year ago by

willowill5

New activity in TheBloke/Falcon-180B-Chat-AWQ over 1 year ago

Quantization not recognized, even when building VLLM from source

2

#1 opened over 1 year ago by

willowill5

New activity in TheBloke/Falcon-180B-Chat-GPTQ over 1 year ago

very slow inference speed on 2x A100 80GB with 4-bit (main branch)

#6 opened over 1 year ago by

willowill5