Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
931 Open 10,149 Closed
931 Open 10,149 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

chat: fix parallel_tool_calls default setting based on model capabilities, add tests for parallel tool calls and structured outputs
#22217 opened Apr 21, 2026 by pwilkin Member Loading…
ggml: add initial MetaX backend integration ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22212 opened Apr 21, 2026 by Dayuxiaoshui Loading…
10
ggml: vectorize ggml_vec_dot_q4_1_q8_1 with WASM SIMD128 ggml changes relating to the ggml tensor library for machine learning
#22209 opened Apr 21, 2026 by sirohikartik Loading…
2
cuda: LRU eviction + overalloc for legacy pool ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22207 opened Apr 21, 2026 by TheTom Loading…
1
6
cuda: flash attention DKQ 320 / DV 256 (MLA) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs python python script changes
#22205 opened Apr 21, 2026 by lnigam Loading…
2
ggml-webgpu: enable FLASH_ATTN_EXT on browser without subgroup matrix ggml changes relating to the ggml tensor library for machine learning WebGPU
#22199 opened Apr 21, 2026 by ArberSephirotheca Contributor Loading…
hexagon: add support for FILL op ggml changes relating to the ggml tensor library for machine learning Hexagon
#22198 opened Apr 21, 2026 by aparmp-quic Contributor Loading…
ggml-cuda: Repost of 21896: Blackwell native NVFP4 support ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#22196 opened Apr 21, 2026 by michaelw9999 Contributor Loading…
Hexagon: DAIG op ggml changes relating to the ggml tensor library for machine learning Hexagon
#22195 opened Apr 21, 2026 by shreyajn Contributor Loading…
hexagon: fix missing v79 entry in libggml-htp.inf ggml changes relating to the ggml tensor library for machine learning Hexagon
#22194 opened Apr 21, 2026 by mengshengwu Contributor Loading…
cuda: add partial eviction on pool OOM ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22193 opened Apr 21, 2026 by leonardHONG Contributor Loading…
6
server: add ipv6 support examples ggml changes relating to the ggml tensor library for machine learning
#22192 opened Apr 21, 2026 by alphaonex86 Loading…
Add IP whitelist with CIDR support to llama-server examples server
#22191 opened Apr 21, 2026 by cabelo Contributor Loading…
3
gguf-py: Read and write empty array. python python script changes
#22189 opened Apr 21, 2026 by zhujunling-nj Loading…
1
Modality conditional adapters examples server testing Everything test related
#22184 opened Apr 20, 2026 by gabe-l-hart Collaborator Loading…
6
Optimize reduction stage of dot product of q4_L/q5_K to q8_K on AVX2 ggml changes relating to the ggml tensor library for machine learning
#22181 opened Apr 20, 2026 by nariox Loading…
cuda: disable MMQ stream-k by default for MoE ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#22174 opened Apr 20, 2026 by nisparks Contributor Loading…
10
ngram-mod: Reset i_last when low acceptance streak occurs
#22168 opened Apr 20, 2026 by treo Loading…
Fix incorrect assertion ggml changes relating to the ggml tensor library for machine learning
#22167 opened Apr 20, 2026 by fiesh Loading…
1
4
common: improve GGUF quantization tag regex
#22164 opened Apr 20, 2026 by v1b3coder Loading…
server: Allow continue in thinking (reasoning prefill) examples server
#22162 opened Apr 20, 2026 by roj234 Contributor Loading…
3
sycl: scalar SWAR byte-subtract in Q6_K MMVQ dot product ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22156 opened Apr 20, 2026 by aicss-genai Loading…
1
server: Support chat_template_kwargs for /v1/messages examples server
#22154 opened Apr 20, 2026 by Soreepeong Loading…
sycl: add GGML_SYCL_USE_ASYNC_MEM_OP env toggle ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22153 opened Apr 20, 2026 by aicss-genai Loading…
1
sycl: Q5_K reorder MMVQ/dequant + Q8_0 reorder MMVQ path ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language
#22152 opened Apr 20, 2026 by aicss-genai Loading…
1
ProTip! Follow long discussions with comments:>50.