From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 8C9613806D7 for ; Sun, 19 Jul 2026 09:29:28 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1784453369; cv=none; b=gO/5Cxhx1sudCoLWquZHn3Mhk0fJeRAvOIbNW5UFYb3iNCRIIpS6fKoUhj4kV0zqtbZ3YQd77V8CaNTWsiPAW3tU5C4DfsQ3f0AMSsPXDgjwxgyOAroqdmfoOesB8eQE0oLtjY+SA0u/ynJkCMHQgpeVLthXsQ/tKkqhVnByppQ= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1784453369; c=relaxed/simple; bh=oGJNIWxTbX5ihoGmLkYQhj5MjU0ZPuNokelE6vz4I1g=; h=Date:From:To:Cc:Subject:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=hvflWk8Kuoy1x7NicueIVowAZ/IWYXIvklZbOYKw+WYOGSoFQhFmRqnMZifszJlNmeOA1vSaOS8BsHWfGmiFvWvig/hXa1VPCqm2okngRHQEgpyhNJm8oDy1KdclngErWJIpZanJZAtwK0ddLGiP4AzNSU+baqQwqrUFwggHoN0= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=OIM4G2AE; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="OIM4G2AE" Received: by smtp.kernel.org (Postfix) with ESMTPSA id D64E71F000E9; Sun, 19 Jul 2026 09:29:26 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1784453368; bh=yQvDnpQXXI5HL3qx8Nmd1brL7/ndpo75SOCARF1f1gg=; h=Date:From:To:Cc:Subject:In-Reply-To:References; b=OIM4G2AEb3LJvjjeBFfrxJtQ32vErDiezrWAzpuxvdMPk7fwbf4wIQ+ZasWQMvMgP 8brlZ0ijnr58tPVKNaKqTWz8rt6Hj5lbc5W1hmglstdqwRt6XUVG1HnGRKgTq87a0h 3yryytbCGU0Z7U+ekP4rVxlTfCe1kg806cUFnCsRbYpqtQRMTyEh5BvTUwxO2mAqtT ObBg73lf5nf/gZHRKCbrIgygTZgZbsZAPg24AghZ6TgAJs4iFZbL6ECodDrfOieNKH zJJxMfnAKu0eQ8r2x/KWiz6uWARg5t21xjH88kXd2sll8Bj8Of89uxEsxRR3RP2dCg Qpq9crE3FH1wQ== Date: Sun, 19 Jul 2026 11:29:24 +0200 From: Mauro Carvalho Chehab To: Takashi Iwai Cc: "Theodore Tso" , Jonathan Corbet , Sasha Levin , ksummit@lists.linux.dev Subject: Re: [MAINTAINERS SUMMIT] Other LLM-related topics - tags, newcomers, etc Message-ID: <20260719112924.2f97086d@foz.lan> In-Reply-To: <87o6g4sl6k.wl-tiwai@suse.de> References: <87wluv7yzc.fsf@trenco.lwn.net> <87y0fa7pdm.fsf@trenco.lwn.net> <20260716215342.30e44c2f@foz.lan> <20260717025812.2397d792@foz.lan> <87o6g4sl6k.wl-tiwai@suse.de> X-Mailer: Claws Mail 4.4.0 (GTK 3.24.52; x86_64-redhat-linux-gnu) Precedence: bulk X-Mailing-List: ksummit@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit On Sat, 18 Jul 2026 11:26:27 +0200 Takashi Iwai wrote: > On Fri, 17 Jul 2026 02:58:12 +0200, > Mauro Carvalho Chehab wrote: > > > > > So it's one say to say, we should figure out how to try to run Sashiko > > > on a local LLM, using open-weight models. But it's going to be a lot > > > easier to propose such a thing than to actually do it. > > > > The main point is: do we really need 671B parameters? Those models > > speak a lot of different languages, have medical databases, and a lot > > of other random knowledge that are useless for kernel development. > > > > I've been playing for a while with qwen 3.6 with 24KB context size, > > 36B parameters (3B activated), 4bits kv quantization and it does produce > > some decent results. The main limitation is the context size: it is > > probably not big enough to test big files (*) > > > > (*) my GPU has 16GB and it is not dedicated to LLM - still, it does > > present results on a reasonable time (a couple of minutes) and > > with decent precision. > > I've been testing the kernel commit reviews with 16GB VRAM GPU, too. > It's an agent program based on Chris Mason's review prompts, and > targeted mainly for the verifications of our backport patches. The > main models I tried were Qwen-3.6 35B, Gemma-4 26B and GPT-OSS 20B > (all 4-bit quantized). And, my conclusion was that even such small > models can catch real bugs. > > Yes, there are definitely many false-positives, and they don't always > follow the recent changes. Also they cover much less changes than > Sashiko. So, the results must be read with lots of grains of salt :) > > The code review is different from the code generation, and the agent > divides the tasks so that the model can concentrate on each small > single task. With that, small models can achieve in some level, too. > > > FWIW, the agent code is found at > https://github.com/tiwai/kernel-review-agent.git > > with HTML renderer and console viewer programs > https://github.com/tiwai/review-table-gen.git > https://github.com/tiwai/kreview-ui-rs.git I just did a Sashiko review test using Ollama locally after applying this PR: https://github.com/sashiko-dev/sashiko/pull/338 The code was AI generated with qwen3.6 with Claude Opus reasoning (hf.co/rico03/Qwen3.6-27B-Claude-Opus-Reasoning-Distilled-GGUF:Q4_K_M). I'll try to play with it a little bit to see how it works with real patch reviews. Thanks, Mauro