Appu Shaji
@appughar.bsky.social
CEO and Founder at Mobius Labs.
Here are for discussions in various facets of AI, such as multimodality, quantisation, efficiency and more. A few of our recent work appears at https://blog.mobiuslabs.com/
Here are for discussions in various facets of AI, such as multimodality, quantisation, efficiency and more. A few of our recent work appears at https://blog.mobiuslabs.com/
Re-distilling a distilled model ( Qwen-Deepseek R1 1.5B ) . Getting few percentage point increase in benchmarks.
Our re-distilled Deepseek R1 (1.5B) outperforms the original distilled model! Get it at huggingface.co/mobiuslabsgm.... We’re distilling more models and look forward to releasing them soon!
January 24, 2025 at 5:36 PM
Re-distilling a distilled model ( Qwen-Deepseek R1 1.5B ) . Getting few percentage point increase in benchmarks.
Super thrilled to release a new version of gemlite, delivering up to 7–8x faster prefill and 3–6x faster batch decoding speed 🚀🚀🚀🚀🚀 compared to PyTorch's tinygemm.
Releasing a new version of Gemlite github.com/mobiusml/gem... significantly improved performance on datacenter GPUS (A100/H100) delivering up to 7–8x faster prefill and 3–6x faster batch decoding compared to PyTorch's tinygemm.
GitHub - mobiusml/gemlite: Fast low-bit matmul kernels in Triton
Fast low-bit matmul kernels in Triton. Contribute to mobiusml/gemlite development by creating an account on GitHub.
github.com
December 5, 2024 at 2:45 PM
Super thrilled to release a new version of gemlite, delivering up to 7–8x faster prefill and 3–6x faster batch decoding speed 🚀🚀🚀🚀🚀 compared to PyTorch's tinygemm.
"Many years later, as he faced the firing squad, Colonel Aureliano Buendía was to remember that distant afternoon when his father took him to discover ice."
Are there other examples of such tense melding in literature?
p.s..: Anticipatory apologies for not using the Spanish version.
Are there other examples of such tense melding in literature?
p.s..: Anticipatory apologies for not using the Spanish version.
December 3, 2024 at 11:31 AM
"Many years later, as he faced the firing squad, Colonel Aureliano Buendía was to remember that distant afternoon when his father took him to discover ice."
Are there other examples of such tense melding in literature?
p.s..: Anticipatory apologies for not using the Spanish version.
Are there other examples of such tense melding in literature?
p.s..: Anticipatory apologies for not using the Spanish version.
This! In general, the goal of any review system should be to verify, reproduce, and push the boundaries of our collective scientific knowledge. Compared to openly reproducible code and evaluations, the merits of rushed and often opinionated reviews are frequently inferior. ( note: very ML specific )
Personally, I assess the quality of a work by studying and running its code, checking its analysis, considering its claims in the light of the data provided, and considering its impact based on my own understanding of the field.
I doubt a random reviewer would do a better job in their limited time.
I doubt a random reviewer would do a better job in their limited time.
November 25, 2024 at 1:44 PM
This! In general, the goal of any review system should be to verify, reproduce, and push the boundaries of our collective scientific knowledge. Compared to openly reproducible code and evaluations, the merits of rushed and often opinionated reviews are frequently inferior. ( note: very ML specific )
Reposted by Appu Shaji
Really happy to contribute to the batched version of faster-whisper that is 4x faster and more accurate 🚀🚀🚀
github.com/SYSTRAN/fast...
github.com/SYSTRAN/fast...
Release faster-whisper 1.1.0 · SYSTRAN/faster-whisper
New Features
New batched inference that is 4x faster and accurate, Refer to README on usage instructions.
Support for the new large-v3-turbo model.
VAD filter is now 3x faster on CPU.
Feature Extr...
github.com
November 25, 2024 at 11:32 AM
Really happy to contribute to the batched version of faster-whisper that is 4x faster and more accurate 🚀🚀🚀
github.com/SYSTRAN/fast...
github.com/SYSTRAN/fast...
Hello, everyone! I love the AI community on X, though not so much the constant squabbling and bickering. I'm here with a faint hope to find more of the former and less of the latter.
November 19, 2024 at 8:30 AM
Hello, everyone! I love the AI community on X, though not so much the constant squabbling and bickering. I'm here with a faint hope to find more of the former and less of the latter.