SourcePulse logo
HomeBrowse all repos
zhyncs avatar

Yineng Zhang

Inference Lead at SGLang; Research Scientist at Together AI

GitHubX

Starred Projects (98)

FastVideo by hao-ai-lab

1.6%
2k
Framework for accelerated video generation
Starred by
hiyouga:
luiscape:
Created 11 months ago
Updated 1 day ago

ThunderKittens by HazyResearch

1.4%
3k
CUDA kernel framework for fast deep learning primitives
Starred by
karpathy:
gakonst:
luiscape:
albertfgu:
+13
Created 1 year ago
Updated 3 days ago

tinker-cookbook by thinking-machines-lab

15.8%
977
Advanced LLM fine-tuning SDK and example cookbook
Starred by
gakonst:
lewtun:
WoosukKwon:
pgarbacki:
+1
Created 3 months ago
Updated 23 hours ago

DeepSeek-V3.2-Exp by deepseek-ai

8.0%
884
Experimental LLM boosting long-context efficiency
Starred by
merrymercy:
Created 2 weeks ago
Updated 1 week ago

checkpoint-engine by MoonshotAI

1.8%
767
Middleware for efficient LLM weight updates during inference
Starred by
pgarbacki:
zhuohan123:
luiscape:
didierrlopes:
+3
Created 1 month ago
Updated 20 hours ago

batch_invariant_ops by thinking-machines-lab

2.0%
823
Enhance LLM inference determinism
Starred by
Edward-Sun:
ekzhang:
willccbb:
zhuohan123:
+1
Created 1 month ago
Updated 1 week ago

xtuner by InternLM

0.3%
5k
LLM fine-tuning toolkit for research
Starred by
casper-hansen:
winglian:
lysandrejik:
JustinLin610:
+2
Created 2 years ago
Updated 22 hours ago

agents.md by openai

3.7%
7k
A format for guiding coding agents
Starred by
transitive-bullshit:
romainhuet:
Created 1 month ago
Updated 6 days ago

axolotl by axolotl-ai-cloud

0.5%
11k
CLI tool for streamlined post-training of AI models
Starred by
tobi:
beyang:
patrickvonplaten:
amiruci:
+25
Created 2 years ago
Updated 1 day ago

DiffSynth-Studio by modelscope

0.8%
10k
Open-source project for diffusion model exploration
Starred by
rodrigosnader:
doriandarko:
Created 1 year ago
Updated 1 day ago

coze-studio by coze-dev

3.3%
18k
AI agent development platform with visual tools
Created 3 months ago
Updated 20 hours ago

Step3 by stepfun-ai

0.2%
428
Multimodal reasoning model for efficient vision-language tasks
Created 2 months ago
Updated 2 months ago

SpecForge by sgl-project

2.2%
423
Train speculative decoding models for faster inference
Starred by
xiezhq-hermann:
Ying1123:
Created 4 months ago
Updated 23 hours ago

chatterbox by resemble-ai

1.1%
14k
Open-source TTS model
Starred by
gakonst:
dguido:
joewalnes:
abidlabs:
+5
Created 5 months ago
Updated 2 weeks ago

Kimi-K2 by MoonshotAI

0.4%
8k
State-of-the-art MoE language model
Starred by
krisr:
lucidrains:
merrymercy:
shizhediao:
+4
Created 3 months ago
Updated 1 month ago

gemini-cli by google-gemini

1.2%
79k
AI agent for terminal workflows
Starred by
MagMueller:
lucidrains:
khou22:
koraykv:
+27
Created 6 months ago
Updated 21 hours ago

trae-agent by bytedance

0.6%
10k
LLM-powered CLI for software engineering tasks
Starred by
hiyouga:
yiranwu0:
syrusakbary:
transitive-bullshit:
+1
Created 4 months ago
Updated 3 weeks ago

Math-Verify by huggingface

1.1%
966
Math evaluator for LLM outputs in mathematical tasks
Starred by
shizhediao:
thomwolf:
hiyouga:
lewtun:
Created 9 months ago
Updated 3 months ago

Skills by NVIDIA-NeMo

2.1%
581
LLM skill-improvement pipelines for synthetic data generation, training, and evaluation
Starred by
winglian:
Created 1 year ago
Updated 21 hours ago

RL-Factory by Simple-Efficient

0.9%
2k
RL post-training framework for agentic learning
Created 4 months ago
Updated 5 days ago

minions by HazyResearch

0.4%
1k
Communication protocol for cost-efficient LLM collaboration
Starred by
JohannesHa:
w4nderlust:
jmorganca:
mchiang0610:
Created 8 months ago
Updated 1 day ago

slime by THUDM

3.5%
2k
LLM post-training framework for RL scaling
Starred by
pgarbacki:
pcmoritz:
casper-hansen:
simonw:
+2
Created 3 months ago
Updated 1 day ago

Hunyuan3D-2.1 by Tencent-Hunyuan

1.8%
2k
Image to 3D asset generation with PBR materials
Starred by
zhuohan123:
Created 4 months ago
Updated 3 weeks ago

dots.llm1 by rednote-hilab

0%
465
MoE model for research
Created 5 months ago
Updated 1 month ago

ROLL by alibaba

2.0%
2k
RL library for large language models
Starred by
yiranwu0:
pcmoritz:
Created 4 months ago
Updated 2 days ago

cosmos-reason1 by nvidia-cosmos

1.6%
748
Multimodal LLMs for physical common sense and embodied decisions
Created 7 months ago
Updated 1 week ago

torchtune by meta-pytorch

0.2%
6k
PyTorch library for LLM post-training and experimentation
Starred by
lewtun:
patrickvonplaten:
JustinLin610:
shizhediao:
+12
Created 2 years ago
Updated 1 day ago

ome by sgl-project

1.4%
289
Kubernetes operator for LLM serving
Starred by
merrymercy:
Ying1123:
Created 4 months ago
Updated 3 days ago

unsloth by unslothai

0.5%
47k
Finetuning tool for LLMs, targeting speed and memory efficiency
Starred by
tobi:
karpathy:
danielhanchen:
yiranwu0:
+36
Created 1 year ago
Updated 1 day ago

RL by NVIDIA-NeMo

1.5%
929
Scalable toolkit for efficient model reinforcement learning
Starred by
hammer:
wangshangsam:
pcmoritz:
willccbb:
Created 7 months ago
Updated 23 hours ago

VeOmni by ByteDance-Seed

1.6%
1k
Framework for scaling multimodal model training across accelerators
Starred by
hiyouga:
JustinLin610:
Created 6 months ago
Updated 22 hours ago

MiMo by XiaomiMiMo

0.2%
2k
LLM for reasoning, pre-trained and post-trained for math/code tasks
Starred by
alexchen4ai:
WoosukKwon:
omarsar:
Created 5 months ago
Updated 4 months ago

dia by nari-labs

0.3%
19k
TTS model for ultra-realistic dialogue generation
Starred by
shimmyshimmer:
alexchen4ai:
omarsar:
codekansas:
+9
Created 5 months ago
Updated 3 months ago

SpargeAttn by thu-ml

1.1%
741
Training-free sparse attention for model inference acceleration
Created 7 months ago
Updated 2 weeks ago

profile-data by deepseek-ai

0.3%
1k
Profiling data for computation-communication overlap analysis
Created 7 months ago
Updated 6 months ago

multi-swe-bench by multi-swe-bench

1.2%
261
Multilingual benchmark for LLM-powered code issue resolution
Created 7 months ago
Updated 1 week ago

aider by Aider-AI

0.3%
38k
AI pair programming in your terminal
Starred by
bcherny:
nat:
hugs:
yiranwu0:
+36
Created 2 years ago
Updated 1 week ago

Triton-distributed by ByteDance-Seed

1.7%
1k
Distributed compiler for computation-communication overlapping, based on Triton
Starred by
antiagainst:
Created 6 months ago
Updated 1 week ago

AReaL by inclusionAI

2.2%
3k
Distributed RL system for LLM reasoning
Starred by
yiranwu0:
casper-hansen:
merrymercy:
Created 7 months ago
Updated 1 day ago

dynamo by ai-dynamo

0.9%
5k
Inference framework for distributed generative AI model serving
Starred by
vincentweisser:
willingc:
chiphuyen:
luiscape:
+7
Created 7 months ago
Updated 20 hours ago

QwQ by QwenLM

0.2%
524
Reasoning model for complex problem-solving, based on Qwen2.5
Starred by
shimmyshimmer:
huybery:
JustinLin610:
Created 7 months ago
Updated 6 months ago

3FS by deepseek-ai

0.3%
9k
Distributed file system for AI training/inference workloads
Starred by
joewalnes:
wesm:
alexey-milovidov:
flaque:
+5
Created 7 months ago
Updated 1 day ago

EPLB by deepseek-ai

0.1%
1k
Load balancer for expert-parallel MoE models
Starred by
parano:
comaniac:
Created 7 months ago
Updated 6 months ago

DualPipe by deepseek-ai

0.1%
3k
Pipeline parallelism algorithm for training large models
Starred by
luiscape:
JohannesHa:
Created 7 months ago
Updated 7 months ago

DeepGEMM by deepseek-ai

0.3%
6k
CUDA library for efficient FP8 GEMM kernels with fine-grained scaling
Starred by
patrickvonplaten:
parano:
shyamal-anadkat:
hammer:
+3
Created 8 months ago
Updated 21 hours ago

DeepEP by deepseek-ai

0.3%
9k
Expert-parallel communication library for MoE, targeting high-throughput and low-latency
Starred by
parano:
JustinLin610:
CodeCreator:
calvinfo:
+3
Created 8 months ago
Updated 1 day ago

FlashMLA by deepseek-ai

0.2%
12k
Efficient CUDA kernels for MLA decoding
Starred by
hammer:
jmorganca:
shizhediao:
suquark:
+5
Created 7 months ago
Updated 2 weeks ago

Moonlight by MoonshotAI

0.2%
1k
MoE model and optimizer tech report
Starred by
jph00:
lucidrains:
Created 7 months ago
Updated 2 months ago

open-infra-index by deepseek-ai

0.0%
8k
AI infrastructure tools for efficient AGI development
Starred by
lattner:
vincentweisser:
hammer:
pankajroark:
+15
Created 7 months ago
Updated 5 months ago

ktransformers by kvcache-ai

0.3%
15k
Framework for LLM inference optimization experimentation
Starred by
luiscape:
patrickvonplaten:
JustinLin610:
shimmyshimmer:
+1
Created 1 year ago
Updated 2 days ago

skypilot by skypilot-org

0.3%
9k
Framework for cloud AI/batch jobs, unifying execution across diverse infrastructure
Starred by
karpathy:
tobi:
amin3141:
luiscape:
+24
Created 4 years ago
Updated 22 hours ago

ZhiLight by zhihu

0%
900
LLM inference engine for Llama and variants, optimized for PCIe GPUs
Starred by
hiyouga:
Created 10 months ago
Updated 3 months ago

Janus by deepseek-ai

0.1%
18k
Unified multimodal model research paper for understanding and generation
Starred by
jiamings:
omarsar:
taranjeet:
xiaofan-luan:
+4
Created 1 year ago
Updated 8 months ago

UI-TARS by bytedance

0.7%
8k
Multimodal agent for GUI interaction in virtual worlds (research paper)
Starred by
jiamings:
hugs:
jmorganca:
omarsar:
+3
Created 8 months ago
Updated 4 days ago

rtp-llm by alibaba

1.6%
884
LLM inference engine for diverse applications
Created 1 year ago
Updated 20 hours ago

tilelang by tile-ai

9.7%
4k
DSL for high-performance GPU/CPU kernel development (GEMM, attention, etc.)
Starred by
hiyouga:
JustinLin610:
luiscape:
zhuohan123:
+1
Created 1 year ago
Updated 22 hours ago

DeepSeek-R1 by deepseek-ai

0.1%
91k
Reasoning models research paper
Starred by
shimmyshimmer:
rasbt:
transitive-bullshit:
omarsar:
+16
Created 8 months ago
Updated 3 months ago

MInference by microsoft

0%
1k
Framework for long-context LLM inference speedup via sparse attention
Starred by
pgarbacki:
Created 1 year ago
Updated 2 weeks ago

flash-linear-attention by fla-org

1.5%
3k
Efficient Torch/Triton implementations for linear attention models
Starred by
hiyouga:
xiezhq-hermann:
yang-song:
winglian:
+8
Created 1 year ago
Updated 2 days ago

MiniMax-01 by MiniMax-AI

1.1%
3k
Large language & vision-language models based on linear attention
Starred by
sxyu:
transitive-bullshit:
omarsar:
hiyouga:
+2
Created 9 months ago
Updated 3 months ago

dash-infer by modelscope

0.4%
266
LLM inference engine for optimized performance across diverse hardware
Created 1 year ago
Updated 2 months ago

smoothquant by mit-han-lab

0.5%
2k
Post-training quantization research paper for large language models
Starred by
zhiyuan8:
gakonst:
forresti:
Edward-Sun:
+1
Created 2 years ago
Updated 1 year ago

picotron by huggingface

0.2%
2k
Minimalist distributed training framework for educational use
Starred by
karpathy:
transitive-bullshit:
srush:
pgarbacki:
+3
Created 1 year ago
Updated 1 month ago

hqq by mobiusml

0.5%
883
Model quantizer for fast, accurate post-training quantization, skipping calibration
Starred by
danielhanchen:
winglian:
hiyouga:
osanseviero:
Created 1 year ago
Updated 1 month ago

torchtitan by pytorch

0.6%
5k
PyTorch platform for generative AI model training research
Starred by
karpathy:
pgarbacki:
lewtun:
zhuohan123:
+11
Created 1 year ago
Updated 21 hours ago

LightLLM by ModelTC

0.5%
4k
Python framework for LLM inference and serving
Starred by
chiphuyen:
pgarbacki:
JustinLin610:
winglian:
+6
Created 2 years ago
Updated 22 hours ago

cline by cline

0.4%
51k
VS Code extension for autonomous coding agent
Starred by
didierrlopes:
swyxio:
snowzurfer:
ishaan-jaff:
+26
Created 1 year ago
Updated 22 hours ago

DeepSeek-V3 by deepseek-ai

0.1%
100k
MoE language model research paper with 671B total parameters
Starred by
tobi:
shimmyshimmer:
jiamings:
syrusakbary:
+13
Created 9 months ago
Updated 1 month ago

infinity by michaelfeil

0.6%
2k
REST API for high-throughput, low-latency embedding and reranking
Starred by
luiscape:
ishaan-jaff:
ankane:
jn2clark:
+8
Created 2 years ago
Updated 1 week ago

Star-Attention by NVIDIA

0%
390
PyTorch code for efficient LLM inference on long sequences
Created 10 months ago
Updated 3 months ago

Qwen3-Coder by QwenLM

0.7%
14k
Code LLM for code completion, generation, and assistant use cases
Starred by
hugs:
victortaelin:
luiscape:
cournape:
+8
Created 1 year ago
Updated 2 months ago

xgrammar by mlc-ai

0.9%
1k
Library for efficient structured generation
Starred by
merrymercy:
ogabrielluiz:
youkaichao:
simonw:
+4
Created 1 year ago
Updated 3 days ago

prompt-lookup-decoding by apoorvumang

0%
572
Decoding method for faster LLM generation
Starred by
stas00:
jph00:
casper-hansen:
ggerganov:
Created 1 year ago
Updated 1 year ago

verl by volcengine

1.5%
14k
RL training library for LLMs
Starred by
hammer:
yiranwu0:
luiscape:
binarybana:
+13
Created 11 months ago
Updated 1 day ago

duo-attention by mit-han-lab

0.2%
494
Framework for efficient long-context LLM inference
Created 1 year ago
Updated 8 months ago

corenet by apple

0.0%
7k
DNN toolkit for training standard and novel models
Starred by
transitive-bullshit:
omarsar:
t3dotgg:
hammer:
+5
Created 1 year ago
Updated 5 days ago

tensorrtllm_backend by triton-inference-server

0.3%
898
Triton backend for serving TensorRT-LLM models
Starred by
NikolaBorisov:
guberti:
Ying1123:
tuhins:
Created 2 years ago
Updated 4 days ago

Pai-Megatron-Patch by alibaba

0.8%
1k
Training toolkit for LLMs & VLMs using Megatron
Starred by
Jiayi-Pan:
Created 2 years ago
Updated 2 days ago

whisper by openai

0.4%
89k
Speech recognition model for multilingual transcription/translation
Starred by
bcherny:
karpathy:
ogabrielluiz:
swyxio:
+40
Created 3 years ago
Updated 1 month ago

TensorRT-LLM by NVIDIA

0.4%
12k
LLM inference optimization SDK for NVIDIA GPUs
Starred by
hammer:
shizhediao:
luiscape:
parano:
+17
Created 2 years ago
Updated 20 hours ago

EAGLE by SafeAILab

1.3%
2k
Speculative decoding research paper for faster LLM inference
Starred by
shizhediao:
philschmid:
pgarbacki:
JustinLin610:
+5
Created 1 year ago
Updated 1 day ago

Nanoflow by efeslab

0.4%
899
LLM serving framework for high throughput
Starred by
WoosukKwon:
Ying1123:
zhuohan123:
Created 1 year ago
Updated 3 weeks ago

truss by basetenlabs

0.1%
1k
Model deployment tool for productionizing AI/ML models
Starred by
apsdehal:
ogabrielluiz:
hammer:
pankajroark:
+4
Created 3 years ago
Updated 1 day ago

mscclpp by microsoft

0.9%
421
GPU-driven communication stack for scalable AI applications
Starred by
jrk:
WoosukKwon:
Created 2 years ago
Updated 2 days ago

ao by pytorch

0.7%
2k
PyTorch library for quantization and sparsity in training/inference
Starred by
shimmyshimmer:
parano:
willccbb:
alexchen4ai:
+10
Created 1 year ago
Updated 1 day ago

simple-evals by openai

0.4%
4k
Lightweight library for evaluating language models
Starred by
patrickvonplaten:
simonw:
philschmid:
Ying1123:
+13
Created 1 year ago
Updated 2 months ago

sglang by sgl-project

0.9%
19k
Fast serving framework for LLMs and vision language models
Starred by
samlambert:
ebursztein:
philschmid:
pankajroark:
+32
Created 1 year ago
Updated 20 hours ago

QuaRot by spcl

0%
430
Code for a NeurIPS 2024 research paper on LLM quantization
Starred by
jph00:
Created 1 year ago
Updated 10 months ago

FlagGems by FlagOpen

0.4%
694
Operator library for LLM training/inference, implemented in Triton
Created 1 year ago
Updated 3 days ago

ring-attention-pytorch by lucidrains

0.2%
540
Pytorch impl of Ring Attention for near-infinite context
Starred by
sxyu:
vincentweisser:
Created 1 year ago
Updated 5 months ago

Mooncake by kvcache-ai

0.8%
4k
Research paper on a disaggregated architecture for LLM serving
Starred by
jiamings:
luiscape:
merrymercy:
WoosukKwon:
+2
Created 1 year ago
Updated 20 hours ago

DeepSeek-V2 by deepseek-ai

0.1%
5k
MoE language model for research/API use
Starred by
gakonst:
jiamings:
Jiayi-Pan:
Created 1 year ago
Updated 1 year ago

llama3 by meta-llama

0.1%
29k
*Deprecated* minimal example for loading and running Llama 3 models
Starred by
tobi:
mckaywrigley:
osanseviero:
simonw:
+13
Created 1 year ago
Updated 8 months ago

mlx by ml-explore

0.2%
22k
Array framework for machine learning on Apple silicon
Starred by
geohot:
karpathy:
jmorganca:
chiphuyen:
+36
Created 1 year ago
Updated 1 day ago

flashinfer by flashinfer-ai

1.1%
4k
Kernel library for LLM serving
Starred by
hammer:
JustinLin610:
luiscape:
youkaichao:
+10
Created 2 years ago
Updated 1 day ago

flash-attention by Dao-AILab

0.6%
20k
Fast, memory-efficient attention implementation
Starred by
karpathy:
Jiayi-Pan:
zhiyuan8:
alexchen4ai:
+31
Created 3 years ago
Updated 1 day ago

Medusa by FasterDecoding

0.2%
3k
Framework for accelerating LLM generation using multiple decoding heads
Starred by
osanseviero:
parano:
luiscape:
chiphuyen:
+6
Created 2 years ago
Updated 1 year ago

lmdeploy by InternLM

0.3%
7k
Toolkit for LLM compression, deployment, and serving
Starred by
shimmyshimmer:
wsxiaoys:
luiscape:
jn2clark:
+8
Created 2 years ago
Updated 1 day ago
Feedback? Help us improve.