Scholar
Ashish Panwar
Google Scholar ID: 2navLOMAAAAJ
Principal Researcher, Microsoft Research India
Operating Systems
Memory Management
Systems for ML
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
1,186
H-index
11
i10-index
12
Publications
20
Co-authors
31
list available
Contact
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
4 items
LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
2026
Cited
1
PyGraph: Robust Compiler Support for CUDA Graphs in PyTorch
2025
Cited
0
POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference
arXiv.org · 2024
Cited
3
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention
arXiv.org · 2024
Cited
12
Resume (English only)
Co-authors
31 total
Jayashree Mohan
Microsoft Research India
Ramachandran Ramjee
Microsoft Research India
Co-author 3
Nipun Kwatra
Computer Science, Stanford University
Co-author 5
Amey Agrawal
PhD Student at Georgia Tech
Alexey Tumanov
Associate Professor, Georgia Institute of Technology
Co-author 8
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up