vladciocan88 (vlad ciocan) – Community Activity

New activity in OpenVINO/mixtral-8x7b-instruct-v0.1-int4-ov 22 days ago

NPU support

#2 opened 22 days ago by

vladciocan88

New activity in Qwen/Qwen3-VL-32B-Instruct about 1 month ago

'Qwen3VLConfig' object has no attribute 'vocab_size'

👀 1

1

#3 opened about 1 month ago by

vladciocan88

New activity in Qwen/Qwen3-Omni-30B-A3B-Instruct about 1 month ago

Configuration needed

#24 opened about 1 month ago by

vladciocan88

New activity in Qwen/Qwen3-VL-30B-A3B-Instruct-FP8 about 2 months ago

model troughput is so low on H100??? anyone else is facing the same issue? using vllm to deploy

👀 1

3

#4 opened about 2 months ago by

sanak

New activity in speaches-ai/piper-ro_RO-mihai-medium 2 months ago

Run example?

#1 opened 2 months ago by

vladciocan88

New activity in Qwen/Qwen3-Omni-30B-A3B-Instruct 2 months ago

Model halucinates when running paralel requests in vllm

#12 opened 2 months ago by

vladciocan88

New activity in Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 2 months ago

HELP, model only halucinates

#6 opened 2 months ago by

vladciocan88

New activity in huggingface/InferenceSupport 3 months ago

unsloth/Qwen2.5-VL-32B-Instruct-bnb-4bit

#4893 opened 3 months ago by

vladciocan88

New activity in SofiTesfay2010/HRM-LLM 3 months ago

Train on multiple GPU

1

#6 opened 3 months ago by

vladciocan88

New activity in Qwen/Qwen-Image-Edit 3 months ago

HW requirements

➕ 17

30

#6 opened 4 months ago by

vladciocan88

New activity in huggingface/InferenceSupport 4 months ago

Qwen/Qwen3-4B-Instruct-2507-FP8

👍 1

1

#4016 opened 4 months ago by

vladciocan88

New activity in nanonets/Nanonets-OCR-s 5 months ago

CUDA Out of Memory

6

#14 opened 5 months ago by

ep5000

Not working with vllm

3

#22 opened 5 months ago by

leonshub

New activity in reducto/RolmOCR 8 months ago

Recomended GPU size

4

#5 opened 8 months ago by

vladciocan88

vlad ciocan

AI & ML interests

Organizations

NPU support

'Qwen3VLConfig' object has no attribute 'vocab_size'

Configuration needed

model troughput is so low on H100??? anyone else is facing the same issue? using vllm to deploy

Run example?

Model halucinates when running paralel requests in vllm

HELP, model only halucinates

unsloth/Qwen2.5-VL-32B-Instruct-bnb-4bit

Train on multiple GPU

HW requirements

Qwen/Qwen3-4B-Instruct-2507-FP8

CUDA Out of Memory

Not working with vllm

Recomended GPU size

vlad ciocan

AI & ML interests

Organizations

vladciocan88's activity

NPU support

'Qwen3VLConfig' object has no attribute 'vocab_size'

Configuration needed

model troughput is so low on H100??? anyone else is facing the same issue? using vllm to deploy

Run example?

Model halucinates when running paralel requests in vllm

HELP, model only halucinates

unsloth/Qwen2.5-VL-32B-Instruct-bnb-4bit

Train on multiple GPU

HW requirements

Qwen/Qwen3-4B-Instruct-2507-FP8

CUDA Out of Memory

Not working with vllm

Recomended GPU size