Skip to content

Pull requests: ggml-org/llama.cpp

New pull request New
1,021 Open 10,766 Closed
1,021 Open 10,766 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

[WebGPU] Check batch_compute_passes before sending passes when not doing GPU profiling ggml changes relating to the ggml tensor library for machine learning WebGPU
#23457 opened May 21, 2026 by nikhilJain17 Contributor Loading…
hexagon: apply repl optimization in flash attn softmax as #22993 ggml changes relating to the ggml tensor library for machine learning Hexagon
#23455 opened May 21, 2026 by njsyw1997 Contributor Loading…
server: expose prompt token counts in /slots endpoint examples server
#23454 opened May 21, 2026 by ScrewTSW Loading…
3
Generalize Adreno MoE kernels on size M ggml changes relating to the ggml tensor library for machine learning OpenCL Issues specific to the OpenCL backend
#23449 opened May 20, 2026 by shawngu-quic Contributor Loading…
app: re-inject subcommand when router spawns children under unified binary examples server
#23442 opened May 20, 2026 by ServeurpersoCom Contributor Loading…
Hip fattn expf approx ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs
#23441 opened May 20, 2026 by a-huk Loading…
2
MoE disk offloading for Metal Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning
#23440 opened May 20, 2026 by kisasexypantera94 Loading…
1
ggml/cpu: skip zero-scale blocks in TQ1_0 and TQ2_0 vec_dot kernels ggml changes relating to the ggml tensor library for machine learning
#23439 opened May 20, 2026 by eriirfos-eng Loading…
3
json-schema-to-grammar: expand PCRE shorthands in pattern strings testing Everything test related
#23436 opened May 20, 2026 by iOptimizeThings Loading…
1
4
doc: fix spec mtp typo documentation Improvements or additions to documentation
#23435 opened May 20, 2026 by ruixiang63 Loading…
1
ui: Add Thinking mode toggle + improve Chat Form Add Action UI examples server/ui
#23434 opened May 20, 2026 by allozaur Contributor • Draft
1
10
mtp: use inp_out_ids for skipping logit computation model Model specific
#23433 opened May 20, 2026 by am17an Contributor Loading…
2
ggml: replace fixed 1GB context pool with growable buffer in meta backend (#22404) ggml changes relating to the ggml tensor library for machine learning
#23432 opened May 20, 2026 by nonml • Draft
1
4
ui: simplify network error handling examples server/ui
#23431 opened May 20, 2026 by socram8888 Contributor Loading…
3
removed unecesary mmproj download when users pass --no-mmproj
#23425 opened May 20, 2026 by ryan-mangeno Contributor Loading…
1
ggml : add GGML_OP_COL2IM_1D (CPU + CUDA) ggml changes relating to the ggml tensor library for machine learning Nvidia GPU Issues specific to Nvidia GPUs testing Everything test related
#23424 opened May 20, 2026 by ServeurpersoCom Contributor Loading…
vulkan: add Flash Attention support for BFloat16 KV cache. ggml changes relating to the ggml tensor library for machine learning Vulkan Issues specific to the Vulkan backend
#23420 opened May 20, 2026 by 0cc4m Contributor Loading…
6
POC: Serving remote LLMs examples server/ui server
#23419 opened May 20, 2026 by Dev-iL • Draft
3
ggml-zendnn : add Q8_0 quantization support AMD ZenDNN Issues related to the AMD ZenDNN backend ggml changes relating to the ggml tensor library for machine learning
#23414 opened May 20, 2026 by z-sachin Contributor Loading…
6
metal : optimize concat kernel and fix set kernel threads Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning testing Everything test related
#23411 opened May 20, 2026 by ggerganov Member • Draft
1 task done
vocab : add Carbon-3B (HybridDNATokenizer) support python python script changes
#23410 opened May 20, 2026 by kashif Loading…
9
fix: skip main_gpu validation when no gpus are available
#23405 opened May 20, 2026 by Dev-iL Loading…
Update documentation with Granite 4.0/4.1 documentation Improvements or additions to documentation
#23404 opened May 20, 2026 by jesus-talavera-ibm Contributor Loading…
2
ui: Improve Git Hooks for UI development examples server/ui
#23403 opened May 20, 2026 by allozaur Contributor Loading…
@allozaur
8
ggml-cpu:Optimized risc-v cpu nvfp4 ggml changes relating to the ggml tensor library for machine learning
#23402 opened May 20, 2026 by ixgbe Contributor Loading…
ProTip! Adding no:label will show everything without a label.