Skip to content

Pull requests: abetlen/llama-cpp-python

New pull request New
111 Open 472 Closed
111 Open 472 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add chat template for gemma models
#2183 opened Apr 13, 2026 by C00kieFact0ry Loading…
fix suppress_stdout_stderr not working in Jupyter notebooks
#2181 opened Apr 13, 2026 by Anai-Guo Loading…
1
fix: prevent KV cache corruption on SWA/ISWA models + hot-path perf
#2180 opened Apr 12, 2026 by avion23 Loading…
perf: vectorize KV cache prefix matching with numpy
#2179 opened Apr 11, 2026 by nausicaalii Loading…
4 tasks done
build: disable soname to reduce binary size
#2177 opened Apr 9, 2026 by Bing-su Loading…
1
feat(example): Updated server example (batch processing, /v1/responses api, response parsing)
#2174 opened Apr 5, 2026 by abetlen Owner Loading…
fix: Add attribute check for sampler in close method
#2173 opened Apr 4, 2026 by usernames122 Loading…
fix(ci): avoid duplicate py3-none release builds
#2172 opened Apr 3, 2026 by abetlen Owner Loading…
feat: add reasoning_effort to chat completions API
#2167 opened Mar 30, 2026 by abetlen Owner Loading…
3
ci: refactor cpu wheel build workflow
#2164 opened Mar 26, 2026 by Bing-su Loading…
1
6
fix: auto-disable mmap when all layers offloaded to GPU (#1964)
#2147 opened Mar 22, 2026 by ljluestc • Draft
1
Clear kv cache and reset tokens after chat completion
#2141 opened Mar 14, 2026 by thisisayushg Loading…
This PR implements the previously stubbed state management methods in the _internals.py module and updates the corresponding API calls in llama.py to use the correct underlying C++ function names.
#2134 opened Mar 5, 2026 by bsides230 Loading…
feat: Add DeepSeek R1 and distilled model support
#2131 opened Mar 1, 2026 by ljluestc • Draft
1
feat: add streaming tool use (rebased #1884 on latest main)
#2129 opened Feb 23, 2026 by XyLearningProgramming Loading…
1
chore: bump conda-incubator/setup-miniconda from v3.1.0 to v3.3.0
#2128 opened Feb 22, 2026 by Aiudadadadf Loading…
fix: correct typos 'seperated' and 'seperator' to 'separated' and 'separator'
#2121 opened Feb 9, 2026 by thecaptain789 Loading…
fix: correct typo 'seperated' to 'separated'
#2120 opened Feb 7, 2026 by thecaptain789 Loading…
feat: support Granite-Docling model
#2109 opened Jan 4, 2026 by dhdaines Loading…
1
Update to llama.cpp 2026-01-01
#2108 opened Jan 1, 2026 by avion23 Loading…
31
Fix issue #2096: Handle URLs with embedded HTTP credentials in _load_image
#2102 opened Dec 10, 2025 by nMaroulis Loading…
chore: update typing-extensions dependency and set github actions setup-python to v6
#2099 opened Nov 28, 2025 by AnvithaCodes Loading…
Fix: Install correct CUDA toolkit during build
#2088 opened Nov 12, 2025 by chamalgomes Loading…
1
1
Fixed issue #1938
#2085 opened Nov 5, 2025 by TNing Loading…
Include x64 directory for CUDA DLLs on Windows
#2083 opened Oct 24, 2025 by ajparsons Loading…
ProTip! What’s not been updated in a month: updated:<2026-03-13.