lm-sys/FastChat

TensorRT-LLM backend support?

Open

#2,595 opened on Oct 21, 2023

View on GitHub
 (3 comments) (7 reactions) (0 assignees)Python (38,959 stars) (4,736 forks)batch import
enhancementgood first issue

Description

Any plan to NVIDIA's new tensorrt llm backend? https://github.com/NVIDIA/TensorRT-LLM/tree/release/0.5.0

Contributor guide

Tech stack
None
Domain
backendmachine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
needs maintainer response
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
None
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
10
Research direction
This issue requests support for TensorRT LLM backend. No maintainer has responded, so the first step is to elicit a response. If approved, review existing backend integrations in FastChat (e.g., 'fastchat/serve') and study TensorRT LLM documentation to design the integration.
TensorRT-LLM backend support? · lm-sys/FastChat#2595 | Good First Issue