Serving 100s of LLMs on 1 GPU with LoRAX - Travis Addair | Stanford MLSys #84

  Рет қаралды 6,447

Stanford MLSys Seminars

Stanford MLSys Seminars

Күн бұрын

Пікірлер: 8
@voncolborn9437
@voncolborn9437 11 ай бұрын
Great presentation. It is interesting to see the practical side of running a bunch of LLMs. Ops makes it happen. Coming from the old, really old, school of computing with massive multi-user, time-share systems, it is interesting to see how no matter how much computing changes, aspects of it remain the same. Through-put, latency, caching and scheduling is still central. All that seems to have changed is the problem domain. We do, in deed, live in intereswting times.
@conan_der_barbar
@conan_der_barbar Жыл бұрын
great talk! still waiting for the open source release 👀
@Gerald-iz7mv
@Gerald-iz7mv 8 ай бұрын
hi, do you have any links to benchmarks you can run to measure latency, throughput for different model and frameworks etc?
@suleimanshehu5839
@suleimanshehu5839 Жыл бұрын
Please create a video on fine tuning MoE LLM using LoRa adapters such as Mixtural 8x7B MoE LLM within your framework
@fastcardlastname3353
@fastcardlastname3353 Жыл бұрын
This shall change the landscape of multiple agents if it's promised.
@mohamedfouad1309
@mohamedfouad1309 Жыл бұрын
Github link😅
@nithinrao7191
@nithinrao7191 Жыл бұрын
Second
@absbi0000
@absbi0000 Жыл бұрын
First
Foundation Models on Consumer Devices - Tianqi Chen | Stanford MLSys #85
47:35
Stanford MLSys Seminars
Рет қаралды 3,9 М.
FOREVER BUNNY
00:14
Natan por Aí
Рет қаралды 41 МЛН
Как Я Брата ОБМАНУЛ (смешное видео, прикол, юмор, поржать)
00:59
Turn Off the Vacum And Sit Back and Laugh 🤣
00:34
SKITSFUL
Рет қаралды 11 МЛН
Monarch Mixer: Making Foundation Models More Efficient - Dan Fu | Stanford MLSys #86
56:32
5 Reasons Why Adapters are the Future of Fine-tuning LLMs
1:01:18
Predibase
Рет қаралды 1,6 М.
Hardware-aware Algorithms for Sequence Modeling - Tri Dao | Stanford MLSys #87
1:19:06
Jack Kraus - c2 the p2 Fellow Update
39:44
C2theP2
Рет қаралды 9
The Next 100x - Gavin Uberti | Stanford MLSys #92
59:21
Stanford MLSys Seminars
Рет қаралды 6 М.
Notes on AI Hardware - Benjamin Spector | Stanford MLSys #88
1:16:48
Stanford MLSys Seminars
Рет қаралды 5 М.
FOREVER BUNNY
00:14
Natan por Aí
Рет қаралды 41 МЛН