https://github.com/ Events collected by UnlimitedPipe 0.3.2 UnlimitedPipe 0.3.2 Fri, 25 Sep 2026 17:36:30 +0000 https://github.com/langchain-ai/langchain/releases/tag/langchain-fireworks%3D%3D1.6.3 97f95731a6c871f9797e Fri, 25 Sep 2026 12:57:38 +0000 Changes since langchain-fireworks==1.6.2 release(fireworks): 1.6.3 (#40834) fix(fireworks): declare native PDF inputs unsupported (#40814) fix(fireworks): preserve malformed tool arguments as diagnostic JSON (#40818) chore(model-profiles): refresh model profile data (#40804) https://github.com/ollama/ollama/releases/tag/v0.40.0-rc0 ce754497d07217e7abab Fri, 25 Sep 2026 03:31:52 +0000 What's Changed Models run on MLX on Apple Silicon by default In this release, model architectures supported by the MLX runner will run by default on Apple Silicon devices. ollama pull qwen3.8 ollama run qwen3.8 During the RC we will be testing and enabling additional models. Full Changelog: https://github.com/ollama/ollama/compare/v0.34.4...v0.40.0-rc0 https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.6.5 ece746245ac2de0c8be5 Thu, 24 Sep 2026 18:11:22 +0000 Changes since langchain-core==1.6.4 release(core): 1.6.5 (#40816) fix(core): abbreviate long tool IDs in XML buffer strings (#40792) https://github.com/langchain-ai/langchain/releases/tag/langchain-openai%3D%3D1.6.6 145be175f889e8307dcd Thu, 24 Sep 2026 11:31:31 +0000 Changes since langchain-openai==1.6.5 release(openai): 1.6.6 (#40800) fix(openai): raise on error events in stream path (#40791) https://github.com/langchain-ai/langchain/releases/tag/langchain-anthropic%3D%3D1.7.4 2c7374fdae64e83fde12 Wed, 23 Sep 2026 17:56:03 +0000 Changes since langchain-anthropic==1.7.3 chore(anthropic): fix integration test cassette (#40790) release(anthropic): 1.7.4 (#40786) fix(anthropic): add Opus 5.5 and GPT-6 profile augmentations (#40785) feat(anthropic,openai): mid-conversation tool changes on SystemMessage (#40758) https://github.com/langchain-ai/langchain/releases/tag/langchain-openai%3D%3D1.6.5 44a9258d2025f86d7b54 Wed, 23 Sep 2026 15:31:52 +0000 Changes since langchain-openai==1.6.4 release(openai): 1.6.5 (#40787) fix(anthropic): add Opus 5.5 and GPT-6 profile augmentations (#40785) feat(anthropic,openai): mid-conversation tool changes on SystemMessage (#40758) https://github.com/ollama/ollama/releases/tag/v0.34.4 044e7d4ff904a170022b Wed, 23 Sep 2026 02:24:43 +0000 What's Changed Structured outputs on thinking models now apply in a single pass, making them faster and more reliable. Fixed intermittent "model not found" errors with a large local library Fixed the macOS app becoming unresponsive when checking if ChatGPT or Codex is running. Qwen 3.8 prompt processing is faster on Apple Silicon. Gemma 4 on Apple Silicon now picks the best image resolution per image, keeping more detail in high-resolution images. Updated llama.cpp, MLX, and XGrammar. Full… https://github.com/langchain-ai/langchain/releases/tag/langchain-openai%3D%3D1.6.4 8ee4b779172f35e4a50e Tue, 22 Sep 2026 22:37:09 +0000 Changes since langchain-openai==1.6.3 release(openai): 1.6.4 (#40775) chore(model-profiles): refresh openai model profile data (#40774) https://github.com/vllm-project/vllm/releases/tag/v0.30.0 7e2b40ccb198a9f61d14 Tue, 22 Sep 2026 05:20:54 +0000 v0.30.0 Highlights This release features 762 commits from 315 contributors (104 new)! New models: DeepSeek-V4.1-Flash (#56214, #56228, #56208) with the whole KV stored in MXFP8 through the FlashMLA V4.1 record on SM100 (#56893), DeepGEMM Mega-mHC (#56962), and async Engram prefetch with Engram DP sharding (#56512); DeepSeek-V4-Flash-Vision-Exp (#54566), also on ROCm (#55107) and with LoRA (#55897); GLM-5.3-Flash (#53906) with EPLB (#55119); K2-Horizon (#55063); Cohere Compass (#54774); Bailing… https://github.com/langchain-ai/langchain/releases/tag/langchain-fireworks%3D%3D1.6.2 b92d1498724d1ccb04a9 Tue, 22 Sep 2026 04:44:04 +0000 Changes since langchain-fireworks==1.6.1 fix(fireworks): use current completions model in LLM tests (#40740) hotfix(fireworks): use available model in LLM tests (#40737) release(fireworks): 1.6.2 (#40735) chore(model-profiles): refresh model profile data (#40665) chore(deps): bump anyio from 4.11.0 to 4.14.2 in /libs/partners/fireworks (#40639) chore(deps): bump urllib3 from 2.7.0 to 2.8.0 in /libs/partners/fireworks (#40587) chore(deps): bump langsmith from 0.12.1 to 0.12.6 in… https://github.com/langchain-ai/langchain/releases/tag/langchain-openrouter%3D%3D0.2.9 ebf988edd28262e79660 Tue, 22 Sep 2026 04:16:11 +0000 Changes since langchain-openrouter==0.2.8 release(openrouter): 0.2.9 (#40736) chore(model-profiles): refresh model profile data (#40705) chore(model-profiles): refresh model profile data (#40685) chore(model-profiles): refresh model profile data (#40665) chore(deps): bump anyio from 4.13.0 to 4.14.2 in /libs/partners/openrouter (#40627) chore(model-profiles): refresh model profile data (#40600) chore(model-profiles): refresh model profile data (#40541) chore(model-profiles): refresh model… https://github.com/open-webui/open-webui/releases/tag/v0.11.4 929b6e69f90d4e78c9fd Mon, 21 Sep 2026 19:25:21 +0000 Added 📉 Far smaller slim image. A slim build now comes down at around 175 MB, near enough 89% smaller than the last release, the local models, the packages around them and the tools that installed them all gone from it; what that changes about the way an instance behaves is set out under Changed below and in the documentation. Commit, Commit 📦 Smaller standard image. The image no longer carries a second copy of Python, two sets of fonts nothing ever loaded, packages nothing imports, or the tool… https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.37.0 5f8f6068d980d8ef1d6a Mon, 21 Sep 2026 07:35:01 +0000 What's Changed Aimdo 0.5.5 + Auto-detect and enable --fast-disk when the disk is fast (CORE-440) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16333 [Partner Nodes] feat(OpenAI): add transparent background support for GPT Image 2 by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16366 Add CFG control to YuE2 Generate Music node. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/16373 Always put text encoder on GPU when dynamic vram on. by @comfyanonymous in… https://github.com/ollama/ollama/releases/tag/v0.34.3 99eaa7724d4088de4ea4 Sat, 19 Sep 2026 00:02:57 +0000 What's Changed GET /api/show now advertises each model's thinking controls and default: Available in the CLI with: ollama show gemma4 thinking levels false, true default true Available in the API with: sh curl http://localhost:11434/api/show -d '{"model": "glm-5.3-flash:cloud"}' json { "thinking": { "values": ["low", "high", "max"], "default": "max" } } Also available on ollama.com directly for cloud models. Nemotron H vision models are now supported on Apple Silicon with MLX Ollama's macOS app… https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.36.0 f3054aca84e7115a3b75 Tue, 15 Sep 2026 22:26:17 +0000 What's Changed Add new model blueprints and reorganize subgraph categories by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/14785 main: bump the AMD Windows VA quota to 4TB (CORE-409) by @rattus128 in https://github.com/Comfy-Org/ComfyUI/pull/16199 [Partner Noes] feat(OpenRouter): add Microsoft mai-image-2.6 models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/16188 quantops: drop the dead ROCm triton arch gate by @0xDELUXA in… https://github.com/ollama/ollama/releases/tag/v0.34.2 0d4ffd546aa20137a71b Tue, 15 Sep 2026 21:21:07 +0000 What's Changed Added first-run setup when running ollama, with options to sign in or continue locally. Setup completion is shared with the desktop app on macOS and Windows. Added ollama://apps to open the desktop app’s Apps page directly on macOS and Windows. Fixed excessive memory growth during long generations with MLX speculative decoding. Updated llama.cpp. Full Changelog: https://github.com/ollama/ollama/compare/v0.34.1...v0.34.2 https://github.com/ollama/ollama/releases/tag/v0.34.1 f9e9eb8116f0a4751423 Mon, 14 Sep 2026 22:14:03 +0000 What's Changed MLX safetensors ollama create no longer experimental. GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization. Improved MLX memory handling on Apple Silicon Runaway repeat token detection now requires 100 repeat tokens for reduced false positives (e.g. OCR) /api/tags is much faster on large model libraries (3.1 s → 294 ms cold in testing), and model capabilities are now reported consistently. Deprecated typicalp: it can no longer be set… https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.35.0 5a3fe6440844cc64d7ee Wed, 09 Sep 2026 19:55:08 +0000 What's Changed [Partner Nodes] chore(Google): drop retiring Veo 2 and Veo 3.0 models by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15883 [Partner Nodes] feat(Recraft): add V4 Styles by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15903 [Partner Nodes] feat(WAN): add WAN3-Prime model support by @bigcat88 in https://github.com/Comfy-Org/ComfyUI/pull/15894 Bump comfyui-frontend-package to 1.51.9 by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15696 Support avif… https://github.com/huggingface/transformers/releases/tag/v5.17.0 2909b10713ae1d9adccc Wed, 09 Sep 2026 15:42:45 +0000 Release v5.17.0 New Model additions HYV4 Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 49B parameters per token. Each MoE layer holds 256 routed experts plus one always-active shared expert and routes every token to 8 of them. The context window is 1M tokens. The architecture combines four features: Multi-head Latent Attention (MLA) compresses keys and values into a low-rank latent (kvlorarank) that kvbproj expands back to one key/value per query… https://github.com/vllm-project/vllm/releases/tag/v0.29.0 5575d3b9e1a7e79e3f4b Wed, 09 Sep 2026 08:54:49 +0000 v0.29.0 Highlights This release features 594 commits from 277 contributors (91 new)! Model Runner V2 is now the default for all models (#53183), completing the rollout that began with pooling models (#48290). MRV2 also gained CUDA graph memory profiling for KV cache auto-sizing (#53306), batch-sharded sampling that cuts per-step logits memory by 1/TP (#50465), prompt embeds (#42963), extracthiddenstates speculation (#49811), padded FULL cudagraph dispatch for uniform decode under spec decode… https://github.com/ollama/ollama/releases/tag/v0.34.0 0c9dbfacce9bf358675d Sat, 05 Sep 2026 23:49:00 +0000 Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output performance on Apple Silicon, adds support for OpenAI-compatible client tool search and response compaction. Full Changelog: https://github.com/ollama/ollama/compare/v0.33.3...v0.34.0 https://github.com/open-webui/open-webui/releases/tag/v0.11.3 a6725ed4adb394530e8a Mon, 31 Aug 2026 14:55:53 +0000 Added ♿ Accessibility mode reaches the menus. Accessibility mode now marks the menu entry you are pointing at and the model already chosen with a stronger background, across the dropdown menus, their submenus, and the model picker together with its filter and compare controls, so those cues carry the contrast the accessibility guidelines ask for in both themes. Commit, Commit 🔄 General improvements. Various improvements were implemented across the application to enhance performance, stability… https://github.com/open-webui/open-webui/releases/tag/v0.11.2 5163c9e26e5c10090e04 Mon, 31 Aug 2026 05:48:23 +0000 Added 🖼️ Richer previews for terminal files. Word documents and slide decks produced in the terminal are now previewed as the finished document rather than an approximation, and every document preview gains a page strip down the side with numbered thumbnails you can click to jump straight to a page, and the notice warning that a preview might differ from the download is gone now that it does not. Commit, Commit, Commit, Commit, Commit ⚡ Less overhead on every message. Deployments without… https://github.com/huggingface/transformers/releases/tag/v5.16.1 483828ef42f6ee623b98 Wed, 26 Aug 2026 14:50:01 +0000 Release v5.16.1 This is a special release as we include GLM! (and a few small fixes) GLM-5.3-Flash GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series. With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks. GLM-5.3-Flash starts from a newly trained base model, with its architecture and training recipe redesigned… https://github.com/huggingface/transformers/releases/tag/v5.16.0 6769447ad40052077fed Wed, 26 Aug 2026 12:35:15 +0000 Release v5.16.0 New Model additions Qwen4-Exp Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with three key components: GatedResidual (GR), Qwen Sparse Attention (QSA), and Per-Layer Embedding (PLE). GR is a Qwen-developed residual architecture that combines Hyper-Connection with GatedNorm. It mixes multiple residual streams with fine-grained elementwise gating before each attention and Mixture-of-Experts (MoE) block, then controls how much of the block output is injected… https://github.com/vllm-project/vllm/releases/tag/v0.28.0 f76be6f5d4aa0827db82 Wed, 26 Aug 2026 09:46:30 +0000 v0.28.0 Highlights This release features 584 commits from 270 contributors (76 new)! Kimi-K3 performance push: a major optimization effort for Kimi-K3 across the stack — Decode Context Parallel (DCP) support (#50484), fused FlashKDA decode and prefill kernels (#50654, #51311, #52458), SiTU activation support for MegaMoE (#50510), GEMM-RS for sequence parallelism (#52079), combined all-gathers with 1.53x kernel-level speedup (#51070), an adaptive speculative token budget delivering 60% better… https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.34.0 5d0b316b0d55065d7636 Wed, 26 Aug 2026 02:09:08 +0000 What's Changed Fix minimax music not working on non dynamic vram. by @comfyanonymous in https://github.com/Comfy-Org/ComfyUI/pull/15588 Add MiniMaxH3AddGuide for anchoring image and audio guides at any frame by @drozbay in https://github.com/Comfy-Org/ComfyUI/pull/15439 chore(openapi): sync shared API contract from cloud@94d0f1b by @comfy-pr-bot in https://github.com/Comfy-Org/ComfyUI/pull/15041 Bump comfyui-frontend-package to 1.49.6 by @comfy-pr-bot in… https://github.com/open-webui/open-webui/releases/tag/v0.11.1 978ce3fb151dbfcba8df Tue, 25 Aug 2026 21:17:57 +0000 Added 🚦 Human in the loop tool approval. Where an administrator has turned it on, you can switch a conversation from letting tools run freely to being asked first, so a model that wants to use a tool stops and waits for you to allow or deny it, one call at a time in a saved conversation, by button or by keyboard shortcut, with your choice remembered for this conversation and for future ones, switching back to running freely releasing anything already waiting, and automations, channel replies… https://github.com/huggingface/transformers/releases/tag/v5.15.1 10b8143111914c6b492f Wed, 19 Aug 2026 10:50:47 +0000 Patch release v5.15.1 This patch most notably solves a few issues with DFlash and MTP candidate generators, as well as an issue where images could sometimes not be processed on accelerator if using Lanczos filter. It contains the following commits: Fix DFlash candidate token device mismatch with devicemap="auto" (#47877) by @sywangyi and @Cyrilvallez Align logit distributions for CandidateGenerators using sampling (#48007) by @Cyrilvallez Fix MTP config when mlplayertypes is absent (#48015) by… https://github.com/Comfy-Org/ComfyUI/releases/tag/v0.33.1 b65e8130fc3278de11bc Thu, 13 Aug 2026 22:18:34 +0000 What's Changed Fix KSamplerAdvanced with addnoise disabled on nested latents by @kijai in https://github.com/Comfy-Org/ComfyUI/pull/15447 Update workflow templates to v0.11.40 by @comfyui-wiki in https://github.com/Comfy-Org/ComfyUI/pull/15522 chore: replace api nodes -> partner nodes in README by @robinjhuang in https://github.com/Comfy-Org/ComfyUI/pull/15519 Fix PreviewAny escaping non-ASCII text in dict and list previews by @christian-byrne in… https://github.com/vllm-project/vllm/releases/tag/v0.27.1 c8369cbfd12301518036 Tue, 11 Aug 2026 10:47:49 +0000 This is a patch release on top of v0.27.0. Support quantized DSpark Markov heads (#50424) https://github.com/vllm-project/vllm/releases/tag/v0.27.0 1050f2ae8765a9b8a525 Mon, 10 Aug 2026 21:18:11 +0000 vLLM v0.27.0 Release Notes Highlights This release features 561 commits from 242 contributors (64 new)! Kimi K3 support with a full stack landing in one release: core model files and kernels (#50089, #50000), Python (#50093) and Rust (#50104) frontends, AttnRes kernels (#50090), DeepGEMM support (#50458), compressed-tensors quantized checkpoints (#50500), DSpark AR fusion (#50242), and an option to shard the shared expert instead of replicating it (#50656). More new models: Qwen3.5 text-only… https://github.com/huggingface/transformers/releases/tag/v5.15.0 5bc225903c9d4dbe9d7c Mon, 10 Aug 2026 10:28:13 +0000 Release v5.15.0 New Model additions Meta Muse Glimmer Muse Glimmer, released today, is Meta’s new multimodal model, especially designed for agentic use cases. Distilled from Muse to 30B parameters, and released under the Apache 2.0 license, it can be deployed to local setups for privacy-aware applications such as coding, document analysis, personal assistants, Claw- or Hermes-like setups. Muse Glimmer is a dense 30B parameter model consisting of: 2B ViT-style encoder for vision (Perception… https://github.com/open-webui/open-webui/releases/tag/v0.11.0 e1ba6959e9cc92912402 Mon, 27 Jul 2026 09:30:15 +0000 Added 🎨 Redesigned interface. Open WebUI has been visually rebuilt from the ground up. All aspects of the User Interface, from the chat view to the admin panel. Now with a narrower conversation column, lighter typography, tidier spacing, consistent menus and dropdowns, clearly outlined text boxes, and settings rearranged. Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit, Commit…