Pull Requests abetlen/llama-cpp-python

feat: update llama.cpp to 92e854ab8

#2318 by abetlen was merged 2026-06-23 14:56

chore: bump version to 0.3.31

#2317 by abetlen was merged 2026-06-20 08:43

feat: update llama.cpp to f449e0553

#2312 by abetlen was merged 2026-06-20 01:05

chore: bump version to 0.3.30

#2311 by abetlen was merged 2026-06-16 07:47

feat: update llama.cpp to e3a74b299

#2310 by abetlen was merged 2026-06-16 06:45

feat: add Pyodide wheel support

#2309 by abetlen was merged 2026-06-16 07:14

feat: update llama.cpp to ggml-org/llama.cpp@6eab47181

#2308 by abetlen was merged 2026-06-15 08:10

feat: update llama.cpp to ggml-org/llama.cpp@6e9007ae6

#2307 by abetlen was merged 2026-06-15 07:55

fix: preserve recurrent/hybrid model state when the full prompt is already cached

#2306 by allthatido was merged 2026-06-22 06:08

fix(ci): use C++ compiler for Docker builds

#2304 by abetlen was merged 2026-06-14 01:04

fix(ci): skip mtmd CLI wrappers in package builds

#2303 by abetlen was merged 2026-06-13 20:19

chore: bump version to 0.3.29

#2302 by abetlen was merged 2026-06-13 19:36

feat(example): use MTMD batch encoding

#2301 by abetlen was merged 2026-06-13 18:16

feat: update llama.cpp to ggml-org/llama.cpp@f05cf4676

#2300 by abetlen was merged 2026-06-13 17:43

feat: update llama.cpp to ggml-org/llama.cpp@3e7bd4f39

#2298 by abetlen was merged 2026-06-12 15:17

feat: update llama.cpp to ggml-org/llama.cpp@ac4cddeb0

#2297 by abetlen was merged 2026-06-11 04:49

feat: update llama.cpp to ggml-org/llama.cpp@76da2450a

#2295 by abetlen was merged 2026-06-10 07:44

feat: update llama.cpp to ggml-org/llama.cpp@e3471b3e7

#2294 by abetlen was merged 2026-06-09 07:19

Add Windows CPU wheel build pipeline

#2293 by rafaelcaires was closed 2026-06-09 18:40

chore(deps): bump pypa/cibuildwheel from 3.4.1 to 4.0.0 dependencies github_actions

#2292 by dependabot[bot] was closed 2026-06-12 20:03

feat(example): support server video inputs and Gemma text tool calls

#2291 by abetlen was merged 2026-06-09 04:49

feat: update llama.cpp to 8f83d6c27

#2290 by abetlen was merged 2026-06-08 15:15

fix(example): correct GPT-OSS tool calling for server example

#2289 by abetlen was merged 2026-06-08 09:25

fix(example): support multi-step Responses tool streaming

#2288 by abetlen was merged 2026-06-08 05:56

fix(example): derive streaming response parser boundaries from schema

#2287 by abetlen was merged 2026-06-08 03:29

fix(ci): repair Linux accelerator wheels for manylinux

#2286 by abetlen was merged 2026-06-08 05:35

fix(example): avoid duplicate streamed response deltas

#2285 by abetlen was merged 2026-06-08 01:48

chore: bump version to 0.3.28

#2284 by abetlen was merged 2026-06-07 23:49

feat(example): align server MTP support with llama.cpp

#2283 by abetlen was merged 2026-06-07 23:19

feat: update llama.cpp to ggml-org/llama.cpp@9e3b928fd

#2282 by abetlen was merged 2026-06-07 22:20