Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Park Soobin
subin
36
5
16
Follow
Aayush-Saini's profile picture
1fann's profile picture
2 followers
·
1 following
https://cv.subin.rs
subin9
soobinpark1
AI & ML interests
LLM inference and serving — vLLM internals, chat templates, tokenization, and NPU/GPU deployment.
Recent Activity
new
activity
1 day ago
vllm-sr/d3-ultra:
Card: state 26B to match the parameter count, add the release date
new
activity
2 days ago
vllm-sr/d3-turbo-NVFP4:
Pass the runtime's states through split_on_oom (TypeError on warmup)
new
activity
2 days ago
vllm-sr/d3-ultra-NVFP4:
Pass the runtime's states through split_on_oom (TypeError on warmup)
View all activity
Organizations
subin
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
New activity in
vllm-sr/d3-ultra
1 day ago
Card: state 26B to match the parameter count, add the release date
#5 opened 1 day ago by
subin
New activity in
vllm-sr/d3-turbo-NVFP4
2 days ago
Pass the runtime's states through split_on_oom (TypeError on warmup)
1
#4 opened 4 days ago by
dan-jacobson-artemis
New activity in
vllm-sr/d3-ultra-NVFP4
2 days ago
Pass the runtime's states through split_on_oom (TypeError on warmup)
1
#2 opened 4 days ago by
dan-jacobson-artemis
liked
a Space
6 days ago
Running
3
System Duo Demos
📚
3
Demos to show System Duo in action
New activity in
vllm-sr/d3-ultra-FP8
17 days ago
Is d3-ultra-FP8 too heavy for production concurrency?
2
#1 opened 17 days ago by
BuiDoan
liked
a model
17 days ago
baidu/Unlimited-OCR-2
Image-Text-to-Text
•
3B
•
Updated
3 days ago
•
598k
•
710
published
2 models
18 days ago
vllm-sr/d3-ultra-INT4
Zero-Shot Classification
•
26B
•
Updated
about 22 hours ago
•
211
•
1
vllm-sr/d3-ultra-FP8
Zero-Shot Classification
•
26B
•
Updated
about 22 hours ago
•
247
•
4
updated
a model
19 days ago
vllm-sr/d3-ultra-INT4
Zero-Shot Classification
•
26B
•
Updated
about 22 hours ago
•
211
•
1
New activity in
vllm-sr/d3-ultra
19 days ago
Serving with vllm-sr
1
#2 opened 20 days ago by
xfalcox
updated
a model
19 days ago
vllm-sr/d3-ultra-FP8
Zero-Shot Classification
•
26B
•
Updated
about 22 hours ago
•
247
•
4
New activity in
vllm-sr/d3-flash
20 days ago
d3-flash on multiple GPUs
4
#5 opened 20 days ago by
FaisaI
New activity in
vllm-sr/vela3-mini
21 days ago
Improving Multilingual Support and NER Accuracy
1
#3 opened 21 days ago by
BuiDoan
New activity in
vllm-sr/vela3-fast
21 days ago
Reject choice questions without criteria on vela3-fast and drop the score claim
1
#2 opened 21 days ago by
subin
New activity in
vllm-sr/vela3-turbo
21 days ago
Return invalid_question for malformed span thresholds and instructions
1
#2 opened 21 days ago by
subin
New activity in
vllm-sr/vela3-flash
21 days ago
Return invalid_question for malformed span thresholds and instructions
1
#3 opened 21 days ago by
subin
New activity in
vllm-sr/vela3-mini
21 days ago
Return invalid_question for malformed span thresholds and instructions
1
#2 opened 21 days ago by
subin
New activity in
vllm-sr/vela3-lite
21 days ago
Return invalid_question for malformed span thresholds and instructions
1
#3 opened 21 days ago by
subin
New activity in
vllm-sr/vela3-turbo
21 days ago
Keep each thread's adapter gate to itself
1
#1 opened 21 days ago by
subin
New activity in
vllm-sr/vela3-flash
21 days ago
Keep each thread's adapter gate to itself
1
#2 opened 21 days ago by
subin
Load more