Submissions from pytorch.org

		PyTorch and VLLM (pytorch.org)
		1 point by andrewstetsenko 18 days ago \| past
		Flux Fast: Making Flux Go Brrr on H100s (pytorch.org)
		1 point by sayak_paul_hf 23 days ago \| past
		Fault Tolerant Llama training (pytorch.org)
		66 points by Mougatine 25 days ago \| past \| 14 comments
		Torch Backends (pytorch.org)
		1 point by fzliu 36 days ago \| past
		VLLM is now a PyTorch Foundation-hosted project (pytorch.org)
		2 points by djhu9 72 days ago \| past
		PyTorch Foundation Expands and Welcomes VLLM and DeepSpeed (pytorch.org)
		2 points by Philpax 72 days ago \| past
		PyTorch 2.7 Release with Blackwell support (pytorch.org)
		3 points by lnyan 85 days ago \| past
		PyTorch 2.7 Release (pytorch.org)
		3 points by jonbaer 86 days ago \| past
		PyTorch 2.7.0 Release (pytorch.org)
		2 points by DreamFlasher 86 days ago \| past \| 2 comments
		Quantization-Aware Training for Large Language Models with PyTorch (2024) (pytorch.org)
		2 points by tosh 3 months ago \| past
		TorchServe is no longer actively maintained (pytorch.org)
		2 points by tbobm 4 months ago \| past
		PyTorch 2.6 (pytorch.org)
		1 point by tosh 5 months ago \| past
		VLLM Joins PyTorch Ecosystem (pytorch.org)
		2 points by reqo 7 months ago \| past \| 1 comment
		Distilling Llama3.1 8B into 1B in torchtune (pytorch.org)
		1 point by tosh 7 months ago \| past
		PyTorch Deprecation of Conda Nightly Builds (pytorch.org)
		3 points by yeldarb 8 months ago \| past \| 1 comment
		PyTorch Deprecation of Conda Nightly Builds (pytorch.org)
		3 points by nmstoker 8 months ago \| past \| 1 comment
		Torch.load flipping default to weights_only=True (pytorch.org)
		2 points by formalsystem 8 months ago \| past
		PyTorch 2.5.0 Release, SDPA CuDNN backend, Flex Attention (pytorch.org)
		1 point by lnyan 9 months ago \| past
		PyTorch Conference 2024 Recap (pytorch.org)
		1 point by jonbaer 9 months ago \| past
		PyTorch Native Architecture Optimization: Torchao (pytorch.org)
		169 points by jonbaer 9 months ago \| past \| 52 comments
		Async Tensor Parallelism in PyTorch (pytorch.org)
		2 points by lnyan 10 months ago \| past
		CUDA-Free Inference for LLMs (pytorch.org)
		3 points by ororm 10 months ago \| past
		PyTorch 2.4 Now Supports Intel GPUs for Faster Workloads (pytorch.org)
		19 points by soulbadguy 10 months ago \| past \| 2 comments
		FlexAttention: The Flexibility of PyTorch with the Performance of FlashAttention (pytorch.org)
		210 points by limoce 11 months ago \| past \| 24 comments
		A guide on good usage of non_blocking and pin_memory() in PyTorch (pytorch.org)
		1 point by yu3zhou4 11 months ago \| past
		Torchchat (pytorch.org)
		2 points by jonbaer 11 months ago \| past
		Torchchat: Accelerating Local LLM Inference on Laptop, Desktop and Mobile (pytorch.org)
		2 points by OutOfHere 11 months ago \| past
		PyTorch 2.4: Python 3.12, AOTInductor freezing (pytorch.org)
		4 points by DreamFlasher 11 months ago \| past
		Int4 Decoding GQA CUDA Optimizations for LLM Inference (pytorch.org)
		1 point by jxmorris12 on June 13, 2024 \| past
		ExecuTorch Alpha: Taking LLMs and AI to the Edge (pytorch.org)
		4 points by brainer on May 1, 2024 \| past \| 1 comment
		More