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 2026-11-18
stories 286

© 2026 RepoJournal Home Showcase How it works Privacy

$ the-wire · showcase

SGLang drops its 0.5.x flags, llama.cpp fixes FP8 qwen4exp conversion

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

SGLang 0.5.x removals now hard-fail at launch with a message naming the replacement, while llama.cpp unblocks conversion of the Qwen3.8-Flash-Next FP8 checkpoints that stopped on master.

[Refactor] server_args: Remove deprecated flags, choice values and environment variables sgl-project/sglang

by hnyls2002

Every spelling deprecated in 0.5.x is gone from server_args.py: a launch that passes one of the flags in REMOVED_FLAGS, on the command line or inside a --config YAML, now stops with a message naming what to use instead, rather than being remapped with a warning or silently ignored. That turns old launch scripts into hard failures, and the mapping is not always one-to-one: --disable-cuda-graph b...

convert : fix FP8 qwen4exp checkpoints (n-gram table scale, block-scaled FP8) ggml-org/llama.cpp

by am17an

FP8 qwen4exp checkpoints (Qwen/Qwen3.8-Flash-Next-FP8, nvidia/Qwen3.8-Flash-Next-NVFP4) store the n-gram PLE table as 128 F8_E4M3 shards behind a single shared BF16 scale and ship no ngram_embedding.weight, so conversion on master aborted with a ValueError naming the tensor it could not map. The fix handles both that layout and block-scaled FP8, which unblocks anyone converting these checkpoint...

[Frontend] Support output logprobs for gpt-oss in the Responses API vllm-project/vllm

by ArkVex

Setting include=["message.output_text.logprobs"] on /v1/responses used to return a 400 for gpt-oss; output-text logprobs now work in both streaming and non-streaming paths, kept in parity. The plumbing is a token_index on each HarmonyParser Segment plus HarmonyContext picking logprobs for output-text tokens, closing the logprobs-plus-harmony TODO left from earlier work.

[Fix] diffusion/security: Use safe_pickle_loads for DiffusionServer inbound requests (#49290) (#49290) sgl-project/sglang

by Kaya Emre Arikan

DiffusionServer inbound requests now go through safe_pickle_loads instead of the default unpickler, which removes arbitrary pickle deserialization from the request path for anyone serving diffusion models through SGLang.

[Feat] [CPU] quantization: Add CPU FP8/INT8 quant ops and compressed-tensors support sgl-project/sglang

by yanbing-j

The long tail: SGLang added CPU FP8/INT8 quantization ops for Xeon/AMX so compressed-tensors linear schemes run through in-tree sgl_kernel instead of falling into CUDA/Triton-only paths, and llama.cpp landed CUDA few-row MMQ for MUL_MAT_ID at 2 to 24 tokens plus Minimax-Music3 in mtmd, while MXFP8 GQA KV caches on NPU now round-trip through L2 HiCache.

Quick answers

What shipped in Local LLMs on November 18, 2026?
SGLang 0.5.x removals now hard-fail at launch with a message naming the replacement, while llama.cpp unblocks conversion of the Qwen3.8-Flash-Next FP8 checkpoints that stopped on master. In total, 138 commits, 138 pull requests, and 10 releases landed.
Who contributed to Local LLMs on November 18, 2026?
16 developers shipped this update, including Aleksander Grygier, anujj, am17an, ngxson, ArkVex, qianlihuang, sajadn, and mgoin, and 8 more.
What were the notable Local LLMs updates?
[Refactor] server_args: Remove deprecated flags, choice values and environment variables, convert : fix FP8 qwen4exp checkpoints (n-gram table scale, block-scaled FP8), and [Frontend] Support output logprobs for gpt-oss in the Responses API.