From 5abe4d7ba2c30713b0e56829b84cfaee202ee09a Mon Sep 17 00:00:00 2001 From: kwisniewski98 Date: Mon, 16 Sep 2024 15:39:47 +0300 Subject: [PATCH 1/2] Move ALiBi to supported features in README_GAUDI.md --- README_GAUDI.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README_GAUDI.md b/README_GAUDI.md index 5109f7ddf9927..644829210125c 100644 --- a/README_GAUDI.md +++ b/README_GAUDI.md @@ -81,13 +81,13 @@ Supported Features - Inference with [HPU Graphs](https://docs.habana.ai/en/latest/PyTorch/Inference_on_PyTorch/Inference_Using_HPU_Graphs.html) for accelerating low-batch latency and throughput +- Attention with Linear Biases (ALiBi) Unsupported Features ==================== - Beam search - LoRA adapters -- Attention with Linear Biases (ALiBi) - Quantization (AWQ, FP8 E5M2, FP8 E4M3) - Prefill chunking (mixed-batch inferencing) From 1a712d5be7127fb8b4b1e9a8d09d62dd6a38a874 Mon Sep 17 00:00:00 2001 From: kwisniewski98 Date: Tue, 17 Sep 2024 12:35:35 +0300 Subject: [PATCH 2/2] Move ALiBi to supported features in gaudi-installation.rst --- docs/source/getting_started/gaudi-installation.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/getting_started/gaudi-installation.rst b/docs/source/getting_started/gaudi-installation.rst index 27bc0186675f1..328f9e723ec71 100644 --- a/docs/source/getting_started/gaudi-installation.rst +++ b/docs/source/getting_started/gaudi-installation.rst @@ -76,13 +76,13 @@ Supported Features - Tensor parallelism support for multi-card inference - Inference with `HPU Graphs `__ for accelerating low-batch latency and throughput +- Attention with Linear Biases (ALiBi) Unsupported Features ==================== - Beam search - LoRA adapters -- Attention with Linear Biases (ALiBi) - Quantization (AWQ, FP8 E5M2, FP8 E4M3) - Prefill chunking (mixed-batch inferencing)