Go
Home
Pricing
FAQ
Install
Home
Pricing
FAQ
Install
Login
via GitHub
ngxson/llama.cpp
Pull Requests
Commits
Open
Closed
Xsn/mtmd placeholder chunks
examples
python
server
#106 opened 2026-05-30 16:37 by
ngxson
Add exaone4 5 (FOR CI)
examples
python
model
#105 opened 2026-05-26 14:28 by
ngxson
(MIRROR) Implement gguf init from buffer
ggml
testing
#104 opened 2026-05-11 10:15 by
ngxson
Mirror https://github.com/ggml-org/llama.cpp/pull/22121
examples
python
testing
#103 opened 2026-04-27 14:34 by
ngxson
(Mirror) Router: Forward form-data to model server
examples
server
#102 opened 2026-04-19 16:52 by
ngxson
(Mirror) cli : Use acquire/release semantics for stopping logic
examples
#101 opened 2026-04-15 15:29 by
ngxson
(WIP) falcon-ocr, for discussion
examples
python
model
#100 opened 2026-04-14 23:11 by
ngxson
[Mirror] anthropic: fix prefix caching
examples
ggml
server
Nvidia GPU
Apple Metal
Hexagon
#98 opened 2026-04-12 15:31 by
ngxson
fix gguf conversion for audio/vision mmproj (FOR CI)
examples
python
testing
model
#95 opened 2026-04-02 14:44 by
ngxson
[Mirror] model : refactor QKV into common build_qkv and create_tensor_qkv helpers
model
#94 opened 2026-04-01 11:08 by
ngxson
wip: server_tools
examples
server
#93 opened 2026-03-18 23:01 by
ngxson
Xsn/chat fix typed content only (for CI)
jinja parser
#87 opened 2026-02-09 20:15 by
ngxson
Xsn/better tensor debug print (FOR CI)
model
#86 opened 2026-02-04 15:52 by
ngxson
[Mirror] server: /v1/responses (partial)
examples
python
server
#85 opened 2026-01-21 08:34 by
ngxson
cli : fix reasoning responses in CLI
examples
server
testing
#84 opened 2026-01-20 15:00 by
ngxson
[Mirror] server : refactor oai_parser_opt, move it to server_chat_params
examples
server
#83 opened 2026-01-19 21:46 by
ngxson
Glm4moelite
python
#82 opened 2026-01-19 19:05 by
ngxson
[Mirror] server: fix memory reservations in populate_token_probs
examples
server
#81 opened 2026-01-19 17:03 by
ngxson
[Mirror] server: improve slots scheduling for n_cmpl
examples
python
server
#80 opened 2026-01-12 17:24 by
ngxson
Xsn/remote preset
documentation
#79 opened 2026-01-08 14:35 by
ngxson
vendor : update cpp-httplib to 0.30.0
examples
python
server
testing
script
#78 opened 2026-01-07 14:56 by
ngxson
server: poc audio gen
examples
server
#77 opened 2026-01-07 11:43 by
ngxson
Demo: HTTP CORS proxy
examples
server
build
devops
#76 opened 2026-01-06 20:17 by
ngxson
Xsn/jinja vm
documentation
examples
python
server
testing
script
#74 opened 2026-01-04 21:53 by
ngxson
[Mirror] feat: Add model pinning feature to protect critical models from LRU eviction
examples
server
#70 opened 2025-12-25 19:55 by
ngxson
[Mirror] server: (preset) add `unsafe-allow-api-override`
examples
server
#68 opened 2025-12-23 11:08 by
ngxson
[Mirror] mtmd: Add DeepSeekOCR Support
documentation
examples
ggml
python
Nvidia GPU
testing
model
#66 opened 2025-12-23 00:01 by
ngxson
[Mirror] New quantization type: Q3_HIFI
documentation
examples
ggml
python
SYCL
Nvidia GPU
Vulkan
testing
Apple Metal
#65 opened 2025-12-22 23:38 by
ngxson
[Mirror] Add Gemma3n multimodal support with MobileNetV5 vision encoder
examples
python
model
#64 opened 2025-12-22 23:17 by
ngxson
(FOR CI) Xsn/server data race
examples
server
#63 opened 2025-12-21 22:51 by
ngxson
Older