hrithik sagar
hrithiksagar-bgen
AI & ML interests
Large Language Models, VLM
Organizations
RuntimeError: FlashAttention forward only supports head dimension at most 256
π 1
5
#30 opened 3 months ago
by
badhon1512
Add vLLM offline inference example for Qwen3.5 -- Added in README.md
#73 opened 3 months ago
by
hrithiksagar-bgen
Create requirements.txt
#7 opened 3 months ago
by
hrithiksagar-bgen
Unable to determine the version compatibilities
1
#6 opened 4 months ago
by
AlfredManan
Adding Offline and Online inference via vLLM Code
#8 opened 10 months ago
by
hrithiksagar-bgen
vLLM Support Query
π 3
3
#2 opened 10 months ago
by
hrithiksagar-bgen
Will smaller models like 7B be released?
β 34
4
#3 opened 10 months ago
by
CelYuan
Dataset Explanation
2
#2 opened 10 months ago
by
hrithiksagar-bgen
STATS
1
#1 opened 10 months ago
by
hrithiksagar-bgen
Added requirement file for transformers
#13 opened 10 months ago
by
hrithiksagar-bgen
Document Images
1
#2 opened 11 months ago
by
hrithiksagar-bgen
Stats
8
#2 opened 11 months ago
by
hrithiksagar-bgen
Inference code
π 1
3
#2 opened 11 months ago
by
hrithiksagar-bgen
Error: 'Kosmos2_5ForConditionalGeneration' from 'transformers' when using the latest transformer version
β 11
12
#7 opened almost 2 years ago
by
Nidhin117
Added VLLM Offline Serve working code.
8
#107 opened 11 months ago
by
hrithiksagar-bgen
FlashInfer requires sm75+
7
#48 opened 12 months ago
by
hrithiksagar-bgen
vLLM FlashAttention3 with A6000
π 17
19
#33 opened 12 months ago
by
YieumYoon
Import error of ImportError of 'Qwen2_5_VLForConditionalGeneration' from transformers library
8
#17 opened over 1 year ago
by
akbarmq01
Dataset Format
#5 opened about 1 year ago
by
hrithiksagar-bgen
Is the dataset available?
#2 opened about 1 year ago
by
hrithiksagar-bgen