vLLM Office Hours - Using NVIDIA CUTLASS for High-Performance Inference - September 05, 2024

  Рет қаралды 2,259

Neural Magic

Neural Magic

Күн бұрын

Пікірлер: 1
@nickellas9882
@nickellas9882 Ай бұрын
Great session - thanks for posting!
vLLM Office Hours - Advanced Techniques for Maximizing vLLM Performance - September 19, 2024
52:35
vLLM Office Hours - Advanced Techniques for Maximizing vLLM Performance - September 19, 2024
Neural Magic
Рет қаралды 1,1 М.
vLLM Office Hours - Speculative Decoding in vLLM - October 3, 2024
1:04:28
vLLM Office Hours - Speculative Decoding in vLLM - October 3, 2024
Neural Magic
Рет қаралды 568
2 MAGIC SECRETS @denismagicshow @roman_magic
00:32
2 MAGIC SECRETS @denismagicshow @roman_magic
MasomkaMagic
Рет қаралды 29 МЛН
龟兔赛跑：好可爱的小乌龟#short #angel #clown
01:00
龟兔赛跑：好可爱的小乌龟#short #angel #clown
Super Beauty team
Рет қаралды 124 МЛН
Я уговариваю своего друга попробовать чипсы Лава Лава
00:57
Я уговариваю своего друга попробовать чипсы Лава Лава
Аришнев
Рет қаралды 3,2 МЛН
Triple kill😹
00:18
Triple kill😹
GG Animation
Рет қаралды 17 МЛН
MIT prof. explains cryptography, quantum computing, & homomorphic encryption
17:47
MIT prof. explains cryptography, quantum computing, & homomorphic encryption
MIT CSAIL
Рет қаралды 4,8 М.
Palantir CEO Alex Karp Opening Remarks | AIPCon 3
9:06
Palantir CEO Alex Karp Opening Remarks | AIPCon 3
Palantir
Рет қаралды 21 М.
How to keep your home network secure in a work-from-home environment | designDATA Training
54:38
How to keep your home network secure in a work-from-home environment | designDATA Training
designDATA
Рет қаралды 104
Unlock Faster and More Efficient LLMs with SparseGPT
42:27
Unlock Faster and More Efficient LLMs with SparseGPT
Neural Magic
Рет қаралды 2,1 М.
Lightning Talk: Harnessing NVIDIA Tensor Cores: An Exploration of CUTLASS & OpenAI..- Matthew Nicely
8:51
Lightning Talk: Harnessing NVIDIA Tensor Cores: An Exploration of CUTLASS & OpenAI..- Matthew Nicely
PyTorch
Рет қаралды 3,1 М.
vLLM Office Hours - FP8 Quantization Deep Dive - July 9, 2024
56:09
vLLM Office Hours - FP8 Quantization Deep Dive - July 9, 2024
Neural Magic
Рет қаралды 1,3 М.
vLLM Office Hours - vLLM on AMD GPUs and Google TPUs - August 21, 2024
48:13
vLLM Office Hours - vLLM on AMD GPUs and Google TPUs - August 21, 2024
Neural Magic
Рет қаралды 576
vLLM Office Hours - Deep Dive into Mistral on vLLM - October 17, 2024
49:38
vLLM Office Hours - Deep Dive into Mistral on vLLM - October 17, 2024
Neural Magic
Рет қаралды 474
CUTLASS A Performant Flexible and Portable Way to Target Hopper Tensor Cores NVIDIA On Demand
49:37
CUTLASS A Performant Flexible and Portable Way to Target Hopper Tensor Cores NVIDIA On Demand
gun
Рет қаралды 182
Optimizing vLLM Performance through Quantization | Ray Summit 2024
38:11
Optimizing vLLM Performance through Quantization | Ray Summit 2024
Anyscale
Рет қаралды 846
2 MAGIC SECRETS @denismagicshow @roman_magic
00:32
2 MAGIC SECRETS @denismagicshow @roman_magic
MasomkaMagic
Рет қаралды 29 МЛН