Extracts: repo, release, stars delta · metadata or bounded excerpt
Retention: D1 event history with canonical source link and deduplication metadata.
Access basis: Public API; token recommended for production rate limits.
Last ingested: 2026-11-17 · run status: success with data
# v0.34.0 **1,061 commits from 412 contributors (120 new).** Thank you! ## TL;DR - **10 new models** (Mistral Large 4, MiniMax-M3.1-Flash, Nemotron-3.5-Transcribe, and more!) - **Extensible KV cache is on by default:** vLLM sizes the KV cache from memory actually free a
# Release v5.23.0 ## New Model additions ### Inkling2 <img width="1200" height="675" alt="image" src="https://github.com/user-attachments/assets/9115e142-1be3-4f79-a51d-ea0e5c25b152" /> Inkling 2 Small is a multimodal model from Thinking Machines Lab that accepts te
<img width="1600" height="900" alt="llama-cpp-v1" src="https://github.com/user-attachments/assets/ed94ed55-ebe2-4aee-bdfc-81bdaa3a3f59" /> Blog post: https://huggingface.co/blog/ggml-org/llama-cpp-v1 ## Overview llama.cpp v1.0.0 removes the deprecated public API and prom
# Patch release v5.22.2 Some in between patch for security and distributed fixes. See the included commits :hugs: - [Distributed] Set device_id only for NCCL (#50281) by @michaelbenayoun and @3outeille - Harden our Jinja sandboxing (#50431) by @Rocketknight1 **Full C
# v0.33.0 ## Highlights This release features 927 commits from 389 contributors (122 new)! * **New models**: Reflection Beam-1.0 (501B MoE, 23B active) with its DFlash2 drafter (#62074), Yandex AliceAI-Foundation-80B-A3B (#57963), Recursive Flint (40B MoE, 2.5B active) (
# Patch release v5.22.1 We just had to fix the documentation! ** [Fix] Remove WIP doc for Ml4 (https://github.com/huggingface/transformers/pull/50124) from @remi-or
#### MoE * **DeepEP v2 dispatcher:** adds an experimental DeepEP v2 backend for the flex token dispatcher ([\#5153](https://github.com/NVIDIA/Megatron-LM/pull/5153)). * **NCCL EP MXFP8 communication (experimental):** adds MXFP8 dispatch-forward and combine-backward communic
## New Models ### Mistral Large 4 (Le Chonk) <img width="1329" height="780" alt="image" src="https://github.com/user-attachments/assets/1cff9ca7-19e3-4622-8db6-fb1cfa842579" /> Mistral Large 4 is Mistral's largest and most capable model to date: a 1 trillion-parameter na
# Patch release v5.21.1 ** Fix rope_scaling setter for configs that assign it during init (#50080 ) We broke remote code loading in vllm, this fixes it sorry everyone!
# PyTorch 2.15.0 Release Notes - [Highlights](#highlights) - [Backwards Incompatible Changes](#backwards-incompatible-changes) - [Deprecations](#deprecations) - [New Features](#new-features) - [Improvements](#improvements) - [Bug fixes](#bug-fixes) - [Performance](#performance)
## Overview This release adds the LiquidAI LFM3 family (text, vision, audio and omni) together with a new experimental streaming-audio API in `mtmd`, and wires realtime audio in and out of the server through the new `/v1/realtime` and `/tts` endpoints. A batch of new architect
# Triton 3.9.0 Release Notes ## Table of Contents - [Dialect & Frontend](#dialect--frontend-39) - [Backend & Compiler](#backend--compiler-39) - [AMD/HIP Backend](#amdhip-backend-39) - [NVIDIA Backend](#nvidia-backend-39) - [Gluon & Layout Improvements](#gluon--layout-im
# Triton 3.9.0 Release Notes ## Table of Contents - [Dialect & Frontend](#dialect--frontend-39) - [Backend & Compiler](#backend--compiler-39) - [AMD/HIP Backend](#amdhip-backend-39) - [NVIDIA Backend](#nvidia-backend-39) - [Gluon & Layout Improvements](#gluon--layout-im
# Release v5.21.0 ## New Model additions ### MiniCPM-OCR MiniCPM-OCR is a document-understanding model from OpenBMB's MiniCPM-V family. It keeps the MiniCPM-V 4.6 architecture, which pairs a SigLIP vision encoder and a window-attention merger with a Qwen3.5 language mo
### CuTe DSL * Bug fixes and improvements: - Fixed an issue with `cute.extern` where functions with zero arguments would generate invalid type signatures. Compiling such functions a second time would fail. - Clear error/warning are now emitted for `CopyUniversalOp` with m
# Patch release: v5.20.2 This patch notably solves an issue where some inputs could loose their original type inside `prepare_inputs_for_generation` in `generate`, leading to problems with multimodal models. It also fixes some other issues listed on the below commits. It co
# v0.32.0 ## Highlights This release features 814 commits from 363 contributors (121 new)! * **Structured decisions and generic parsers**: the new `POST /v1/systemone` endpoint answers `choice`, `noul` and `score` questions over a structured state (#59299), is served by
# Release v5.20.1 Special surprise including the new model Beam from Reflection AI :partying_face: <img width="2912" height="1440" alt="Gemini_Generated_Image_ox4hjlox4hjlox4h" src="https://github.com/user-attachments/assets/bfc7ff16-4340-490c-925c-b1512e4ceb32" /> Beam
# Release v5.20.0 ## New Model additions ### Muse Spark Open <img width="2400" height="1296" alt="image" src="https://github.com/user-attachments/assets/bf34ea27-0edf-4ded-ba6f-905b04096126" /> Muse Spark Open is a multimodal mixture-of-experts model from Meta that
# Release v5.19.0 ## New Model additions ### EmbeddingGemma2 <img width="2716" height="2308" alt="image" src="https://github.com/user-attachments/assets/84734e74-163d-4d12-b166-ffcf6749d563" /> EmbeddingGemma 2 is a multimodal embedding model from Google built on th
## Overview llama.cpp v0.6.0 introduces the new `llama_batch_ext` extended batch API (with `llama_process`) for mixed token/embedding inputs and MTP/deepstack state embeddings, adds support for the GLM-5.3-Flash (GLM5-Next) 320B hybrid model, the Clef decision model (text and
# v0.31.0 ## Highlights This release features 717 commits from 307 contributors (96 new)! * **DeepSeek-V4.1-Flash performance**: FlashMLA mega attention with the V4.1 NVFP4 compressed KV cache is now the SM100 default (#56935); DeepGEMM sparse MQA logits for the indexer
This release is meant to fix the following regressions and silent correctness issues: ## Silent correctness fixes - Fix incorrect `torch.linalg.lstsq` solutions on MPS for complex batched underdetermined systems ([#196113](https://github.com/pytorch/pytorch/issues/196113)), f
## New Model additions ### Nemotron 3 Diarization <img width="1680" height="900" alt="image" src="https://github.com/user-attachments/assets/fe735cb3-9e5b-43ad-8f60-9dec8425aec7" /> Nemotron 3 Diarization is an open-weight streaming speaker diarization model designed t
## Overview This release focuses on backend performance and correctness, broader model coverage, and more robust server/router operation. It adds HRM-Text (DFM Mimir 1B) support, MiMo-V2.6 and HunyuanOCR conversion support, ggml 0.25.0 backend improvements, multi-address HTTP
# 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
### CuTe DSL * New features - Initial Rubin support to accelerate dense GEMMs. The following features are available: - CuTe DSL and CuTe extensions - Support for higher-throughput FP8 (MMA_K=64) and FP4 (MMA_K=128) Tensor Core MMA instructions - B collect
- TransformerEngine upgraded from 2.17 to 2.18 - Added support for FP4 in 1F1B A2A overlap ([#6135](https://github.com/NVIDIA/Megatron-LM/pull/6135)) <details><summary>Changelog Details</summary> - ci: Revert version update (0.19.1) by @balasaajay :: PR: #6681 - beep boop
## Overview llama.cpp 0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0. ### API changes - Changed `llama_sampler_chain_n()` to return `int3
# Release v5.17.0 ## New Model additions ### HYV4 <img width="1503" height="827" alt="image" src="https://github.com/user-attachments/assets/e6ed85ee-eb1d-40eb-a0d4-c649f6337ca9" /> Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 4
# 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
## Overview llama.cpp 0.4.0 adds initial Qwen3.8-Flash-Next and Nemotron-3-Puzzle support, on-demand tensor reading, per-slot server context limits, video input options, and a ggml update to 0.23.0 with major sparse flash attention and RDMA work. ### API changes - Added
# PyTorch 2.14.0 Release Notes - [Highlights](#highlights) - [Backwards Incompatible Changes](#backwards-incompatible-changes) - [Deprecations](#deprecations) - [New Features](#new-features) - [Improvements](#improvements) - [Bug fixes](#bug-fixes) - [Performance](#perfo
# Triton 3.8.0 Release Notes ## Table of Contents - [Dialect & Frontend](#dialect--frontend) - [Backend & Compiler](#backend--compiler) - [AMD/HIP Backend](#amdhip-backend) - [NVIDIA Backend](#nvidia-backend) - [Gluon & Layout Improvements](#gluon--layout-improvements)
# Triton 3.8.0 Release Notes ## Table of Contents - [Dialect & Frontend](#dialect--frontend) - [Backend & Compiler](#backend--compiler) - [AMD/HIP Backend](#amdhip-backend) - [NVIDIA Backend](#nvidia-backend) - [Gluon & Layout Improvements](#gluon--layout-improvements)
### CuTe DSL * New features - Initial Rubin support to accelerate dense GEMMs. The following features are available: - CuTe DSL - Rubin new FP8 and FP4 Tensor Core support - B collector reuse - Extended TMEM size from 512 COL to 576 COL - L
# Release v5.16.1 This is a special release as we include GLM! (and a few small fixes) # GLM-5.3-Flash <img width="4239" height="2643" alt="image" src="https://github.com/user-attachments/assets/17bc9c29-758b-44c8-8230-42f945ded209" /> GLM-5.3-Flash, the first **nativ
# Release v5.16.0 ## New Model additions ### Qwen4-Exp <img width="2241" height="693" alt="image" src="https://github.com/user-attachments/assets/c838b5ba-ffea-42da-baa9-3f66178e3671" /> Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with thre
# 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
### CuTe DSL * Bug fixing and improvements - Fixed a failed kernel compilation issue when setmaxnreg is used together with specific warp-specialized patterns ([!3420](https://github.com/NVIDIA/cutlass/issues/3420)) - Fixed a leak with jit/kernel decorator ([!3421](https:/
### CuTe DSL * Bug fixing and improvements - Fixed a failed kernel compilation issue when setmaxnreg is used together with specific warp-specialized patterns ([!3382](https://github.com/NVIDIA/cutlass/issues/3420)) - Fixed a leak with jit/kernel decorator ([!3421](https:/
## Overview
## Overview New version has been released. **Nightly build:** [b10566](https://github.com/ggml-org/llama.cpp/releases/tag/b10566) **Web UI:** the `nightly-tag.txt` asset contains the tag of the corresponding nightly release **More info:** [dist : releases and versioning of gg
<details open> TP: enable tensor split for LFM2/LFM2MOE (#26993) Assisted-by: deepseek-v4-flash </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/42096995> **macOS/iOS:** - [macOS Apple Silicon (arm64)](htt
<details open> metal : clamp K extent in tensor API mat-mat kernel for K not a multiple of 32 (#27450) The Tensor API mat-mat path of kernel_mul_mm (GGML_METAL_HAS_TENSOR) fed a static K=32 tile to the matmul2d op on every iteration. On the last, partial K tile (ne00 % 32 != 0)