RepoJournal
Local LLMs Local LLMs
122 wires and counting

$ follow Local LLMs

Keep up with Local LLMs in about 3 minutes: what actually shipped — the commits, pull requests, releases, and security advisories that matter.

or

fair warning: these emails are deeply technical. diffs, version numbers, CVEs, benchmark deltas. if that's not your idea of a good read, this isn't your newsletter.

Folds into your digest — weekly by default, monthly if you prefer. Unsubscribe in one click.

$ status

wire 2026-11-22
stories 230

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

vLLM ships five security fixes; SYCL gets the optimization push

By RepoJournal · Filed · About Local LLMs · Composed from the cited sources · methodology

vLLM closed three distinct memory and input-handling holes in one batch while llama.cpp and sglang spent the day on backend kernels and diffusion tail latency.

[Security] Widen int32 pointer arithmetic to int64 in CUDA kernels (#53131) vllm-project/vllm

by Juan Pérez de Algaba

Pointer arithmetic in the CUDA kernels now runs in int64 instead of int32, which the commit titles under a security tag. Anything driving very large allocations or offsets through those kernels was previously open to overflow; rebuild vLLM from a commit that includes this change before running untrusted or large-context workloads.

[Security] Share media byte budgets across batched requests (#68249) vllm-project/vllm

by Juan Pérez de Algaba

Media byte budgets are now shared across batched requests rather than accounted per request, so a batch of individually-within-limit multimode inputs can no longer exceed the intended total. This changes how multimodal batched serving behaves under load: expect different admission behavior for large image or audio batches.

fix(security): enforce prompt-count bound on pooling and scoring routes (#53473) vllm-project/vllm

by Juan Pérez de Algaba

The pooling and scoring routes now enforce a bound on prompt count, closing the same class of unbounded-input path already guarded on generation endpoints. Deployments exposing /pooling or scoring to untrusted callers should pin a build containing the fix.

fix(security): use segment-boundary-aware root_path stripping in auth middleware (#52794) vllm-project/vllm

by Juan Pérez de Algaba

Auth middleware strips root_path on segment boundaries instead of by prefix, so a path crafted to look like it sits under the root no longer passes through the prefix check. This is the one with the most direct exposure for anyone running vLLM behind a reverse proxy with a non-empty root_path.

sycl: add IQ4_NL and IQ4_XS weight reorder ggml-org/llama.cpp

by Titaniumtown

Weight reordering for IQ4_NL and IQ4_XS on the SYCL backend cuts MUL_MAT time on an Intel Arc B70 from 315.9 to 70.1 microseconds at n=1 and from 944.2 to 87.0 at n=3, a speedup that grows with batch width. If you serve IQ4 weights on Arc hardware, this is the change to benchmark yourself.

[Fix] diffusion: Reject a LoRA adapter that matches no LoRA layer sgl-project/sglang

by ruiling-smartbear

set_lora used to log "LoRA adapter ... did not match any LoRA layer" as a warning and return OK, silently serving the base model; this rejects the adapter instead. The scale is large: in a sample of 826 popular Hub LoRAs for Wan, Qwen-Image, FLUX and LTX-2, 116 files load zero layers on current main, and those will now fail loudly rather than quietly degrade output.

fix empty output handling in many primitives ml-explore/mlx

by nwh

Every primitive was expected to call set_data on all output arrays, and empty outputs such as shape (16, 0) produced a malloc(0) buffer; when a primitive skipped it, results segfaulted on eval. The example in the report, mx.array_equal on an empty matmul result, crashed reliably and no longer does.

Quick answers

What shipped in Local LLMs on November 22, 2026?
vLLM closed three distinct memory and input-handling holes in one batch while llama.cpp and sglang spent the day on backend kernels and diffusion tail latency. In total, 110 commits, 110 pull requests, and 10 releases landed.
Who contributed to Local LLMs on November 22, 2026?
13 developers shipped this update, including clemenswasser, allozaur, Titaniumtown, ngxson, Juan Pérez de Algaba, metamergebot, ChangLiu0709, and mickqian, and 5 more.
What were the notable Local LLMs updates?
[Security] Widen int32 pointer arithmetic to int64 in CUDA kernels (#53131), [Security] Share media byte budgets across batched requests (#68249), and fix(security): enforce prompt-count bound on pooling and scoring routes (#53473).