Michael Goin

mgoin's activity

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

New activity in GadflyII/GLM-4.7-Flash-MXFP4 about 2 months ago

Update MXFP4 format to compressed-tensors

1

#3 opened about 2 months ago by

mgoin

New activity in inference-optimization/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 3 months ago

Fix invalid config

#1 opened 3 months ago by

mgoin

New activity in kernels-community/vllm-flash-attn3 7 months ago

Support for B200s?

👀 5

3

#7 opened 8 months ago by

shriramc

New activity in RedHatAI/Mistral-Small-3.2-24B-Instruct-2506-FP8 9 months ago

Quantization recipe?

2

#3 opened 9 months ago by

veden

Not working with vLLM 0.9.1

5

#1 opened 10 months ago by

zacksiri

New activity in RedHatAI/Llama-3.2-3B-Instruct-quantized.w8a8 9 months ago

Update config.json with the correct state

#1 opened 9 months ago by

dsikka

New activity in MiniMaxAI/MiniMax-Text-01 10 months ago

Make model config compatible with Hugging Face MiniMax implementation

5

#39 opened 10 months ago by

geetu040

New activity in mistralai/Magistral-Small-2506 10 months ago

Missing Tokenizer/Processor for use with Transformers

👍 1

5

#3 opened 10 months ago by

mgoin

New activity in RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic 11 months ago

How should I input the image?

1

#3 opened 11 months ago by

CyberWolf0

New activity in RedHatAI/Qwen2.5-VL-72B-Instruct-quantized.w8a8 12 months ago

用vllm serve启动不了

1

#2 opened about 1 year ago by

VenomEY

New activity in RedHatAI/Qwen2.5-VL-72B-Instruct-FP8-dynamic 12 months ago

Fix processor_class to match upstream

#4 opened 12 months ago by

zifeitong

New activity in RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-dynamic 12 months ago

Remove image_processor_type

#1 opened about 1 year ago by

pooya-davoodi-parasail

New activity in nm-testing/Llama-3_1-Nemotron-Ultra-253B-v1-FP8-dynamic 12 months ago

OSError: nm-testing/Llama-3_1-Nemotron-Ultra-253B-v1-FP8-dynamic does not appear to have a file named decilm.py

2

#2 opened 12 months ago by

TheDrummer

how to deploy this model without internet connection

1

#1 opened about 1 year ago by

superahn

New activity in RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic about 1 year ago

Why not FP8 with static and per-tensor quantization?

👍 1

2

#2 opened about 1 year ago by

wanzhenchn

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 about 1 year ago

Address discrepancies in the languages supported by the Mistral Small 3.1 2503

🔥 1

3

#54 opened about 1 year ago by

fpaupier

New activity in RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic about 1 year ago

Please update the chat template

1

#1 opened about 1 year ago by

stelterlab

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 about 1 year ago

FP8 Dynamic/W8A16 Quants Please

6

#44 opened about 1 year ago by

rjmehta

Problem hosting the model using vllm

➕ 3

5

#45 opened about 1 year ago by

ShaoServient

New activity in RedHatAI/Qwen2.5-VL-72B-Instruct-quantized.w8a8 about 1 year ago

Remove image_processor_type

#1 opened about 1 year ago by

pooya-davoodi-parasail