ggml-org news
The latest ggml-org news, : Ggml-org/llama.cpp merges PR #31283 adding video input for LFM3 models.
The stories describe ggml-org as the maintainer of the llama.cpp repository, where contributors like ggerganov and alexey-rsi merge code. Recent updates include adding support for models such as FlintForCausalLM, Mellum2.1, and Qwen4Exp, alongside performance improvements like fused Vulkan kernels, WebGPU quantization, and new batch control flags.
13 stories mentioning ggml-org since 16 September 2026, newest first, each with its sources and discussion. Follow to see new ones on your front page.
-
Ggml-org/llama.cpp merges PR #31283 adding video input for LFM3 models
The llama.cpp project merged pull request 31283 on October 27, 2026, enabling video input support for the LFM3 model family within the mtmd component. The PR was co-authored by Xuan Son Nguyen (son@huggingface.co) and…
2 sources primary sourcegithub.com -
Ggml-org merges webgpu Q2_0 support into llama.cpp
A pull request (PR 30914) adding Q20 quantization support for WebGPU was merged into the ggml‑org/llama.cpp repository. The change, labeled “merge ready” by maintainer yomaytk on Oct 21‑22, 2026, updates the ggml…
2 sources primary sourcegithub.com -
Ggml-org adds FlintForCausalLM model to llama.cpp
The ggml‑org/llama.cpp repository merged pull request 30928, introducing the FlintForCausalLM model. The contribution was authored by user alexey‑rsi and approved by reviewers ggerganov and CISCapproved. The change…
1 source primary sourcegithub.com -
Ggml-org adds MTP support for Mellum2.1 in llama.cpp Pull Request
A pull request on the ggml-org/llama.cpp repository has been merged, adding MTP support for the Mellum2.1 model. The change was approved and integrated into the codebase. The article does not specify who authored the…
1 source primary sourcegithub.com -
Ggml-org adds fused top‑k mask operation to llama.cpp
A pull request to the ggml‑org/llama.cpp repository introduces a new fused operation for QSA masking. The change adds the GGMLOPTOPKMASK node to the CUDA backend, allowing the mask to be applied per‑head with optional…
1 source primary sourcegithub.com -
Add Nemotron Super 3.5 VL and Nemotron Bolt 74B A9B support by frozenblade1224 · Pull Request #30520 · ggml-org/llama.cpp
The merge, performed by ggerganov, incorporated nine commits that introduce model‑specific multimodal functionality for video, image, and audio conversion. The changes were reviewed and approved by several community…
1 source primary sourcegithub.com -
Ggml-org adds `--spec-draft-n-ubatch` to llama.cpp for batch control
llama.cpp now lets users set a custom physical batch size for draft context via the --spec-draft-n-ubatch flag. The change, merged in a pull request by ggml-org, allows drafts to process tokens in smaller chunks than…
1 source primary sourcegithub.com -
Ggml-org halves indexer score memory in llama.cpp Pull Request
The ggml‑org team submitted a pull request to the llama.cpp repository that changes how the indexer scores are stored during inference. By giving each attention head its own product and summing the results in‑place,…
1 source primary sourcegithub.com -
Qwen4Exp adds MTP support in llama.cpp pull request
A pull request merged into the llama.cpp repository on October 1, 2026, adds support for MTP (likely referring to Mixture of Token Predictions or a similar technique) to the Qwen4Exp model. The change was approved by…
2 sources primary sourcegithub.com -
Ggml-org merges Vulkan kernel fusion for Qwen4exp's SCALE‑sigmoid‑SCALE chain
A pull request (29520) was merged into the ggml‑org/llama.cpp repository on Sep 28 2026, adding a fused Vulkan kernel that combines the SCALE‑SIGMOID‑SCALE‑hcpost operations used by the Qwen4exp model. The change was…
1 source primary sourcegithub.com -
Llama.cpp expert-pool fork for Qwen 3.8 Flash next IQ4 + 16Gb VRAM tested on MI50 gfx906 with parameters
An unofficial fork of llama.cpp introduces a persistent expert pool for mixture‑of‑experts (MoE) models that are offloaded with the --n-cpu-moe flag. Upstream llama.cpp lacks an expert cache, and earlier forks admitted…
1 source primary sourcegithub.com -
Llama.cpp b11003 adds HRM-Text support for DFM Mimir 1B model
The llama.cpp project released version b11003, introducing support for the HRM‑Text architecture used by the DFM Mimir 1B model. The new implementation runs two transformer stacks—low and high—in an alternating cycle…
1 source primary sourcegithub.com -
Ggml-org Merges hc Ops into qwen4exp Graph in llama.cpp
A recent pull request (28901) in the open‑source llama.cpp repository has added new high‑capacity (hc) operations to the qwen4exp graph, targeting both CPU and CUDA backends. The changes fuse a per‑element gate into…
1 source primary sourcegithub.com
Questions about ggml-org
What is the latest ggml-org news?
As of 25 October 2026: Ggml-org/llama.cpp merges PR #31283 adding video input for LFM3 models. The llama.cpp project merged pull request 31283 on October 27, 2026, enabling video input support for the LFM3 model family within the mtmd component.
What is ggml-org?
The stories describe ggml-org as the maintainer of the llama.cpp repository, where contributors like ggerganov and alexey-rsi merge code. Recent updates include adding support for models such as FlintForCausalLM, Mellum2.1, and Qwen4Exp, alongside performance improvements like fused Vulkan kernels, WebGPU quantization, and new batch control flags.