Skip to content

Pull requests: auroralabs-loci/llama.cpp

New pull request New
1,205 Open 156 Closed
1,205 Open 156 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

UPSTREAM PR #22129: Tensor-parallel: Fix delayed AllReduce on Gemma-4 MoE
#1361 opened Apr 20, 2026 by loci-dev Loading…
1
UPSTREAM PR #22102: fix: GLM-DSA crash in llama-tokenize when using vocab_only
#1360 opened Apr 19, 2026 by loci-dev Loading…
1
UPSTREAM PR #22101: mtmd: add granite-speech support (ibm-granite/granite-4.0-1b-speech)
#1359 opened Apr 19, 2026 by loci-dev Loading…
1
UPSTREAM PR #22070: ggml-cuda: gate native ue4m3 conversion to sm_90+
#1358 opened Apr 18, 2026 by loci-dev Loading…
1
UPSTREAM PR #22066: sycl: Battlemage (BMG) optimizations — AOT, Q5_K reorder, PAD stride fix, new ops, oneMKL routing
#1357 opened Apr 18, 2026 by loci-dev Loading…
1
UPSTREAM PR #22023: mtmd: add missing struct tag
#1356 opened Apr 17, 2026 by loci-dev Loading…
UPSTREAM PR #21647: ci: add android arm64 build and release
#1355 opened Apr 17, 2026 by loci-dev Loading…
UPSTREAM PR #21985: Feat/modelscope support
#1354 opened Apr 16, 2026 by loci-dev Loading…
2
UPSTREAM PR #21071: hexagon: optimize HMX matmul operations
#1351 opened Apr 15, 2026 by loci-dev Loading…
1
UPSTREAM PR #21652: Prevent the sum of the dequantized activation in q8_1 from overflowing
#1350 opened Apr 15, 2026 by loci-dev Loading…
1
UPSTREAM PR #21870: common: skip reasoning budget sampler when no budget is requested
#1349 opened Apr 14, 2026 by loci-dev Loading…
1
UPSTREAM PR #21835: Expose build_info in router mode
#1348 opened Apr 13, 2026 by loci-dev Loading…
1
UPSTREAM PR #21821: llama : add --hugepages for HugeTLB-backed weight loading (Linux)
#1347 opened Apr 13, 2026 by loci-dev Loading…
1
UPSTREAM PR #21554: hexagon: optimization for HMX mat_mul
#1346 opened Apr 12, 2026 by loci-dev Loading…
1
UPSTREAM PR #21787: vulkan: fix output corruption on GCN 2.0/3.0 (Vulkan 1.2)
#1345 opened Apr 12, 2026 by loci-dev Loading…
1
UPSTREAM PR #21753: vulkan: Support asymmetric FA in coopmat2 path
#1344 opened Apr 11, 2026 by loci-dev Loading…
1
UPSTREAM PR #21629: cuda: Q1_0 initial backend
#1343 opened Apr 11, 2026 by loci-dev Loading…
1
UPSTREAM PR #21344: gfx1151 nwarps, tile sizing to curb VGPR pressure
#1342 opened Apr 10, 2026 by loci-dev Loading…
1
UPSTREAM PR #21431: vulkan: Tweak Xe2 warptile configuration
#1341 opened Apr 10, 2026 by loci-dev Loading…
1
UPSTREAM PR #21597: SYCL: fix multi-GPU system RAM exhaustion by using Level Zero allocations
#1340 opened Apr 8, 2026 by loci-dev Loading…
7 tasks done
1
UPSTREAM PR #21573: autoparser: fix MiniMax handling
#1339 opened Apr 8, 2026 by loci-dev Loading…
1
UPSTREAM PR #21540: metal : add XIELU op
#1338 opened Apr 7, 2026 by loci-dev Loading…
2 tasks done
1
UPSTREAM PR #21539: vulkan: Support Q1_0
#1337 opened Apr 7, 2026 by loci-dev Loading…
1
UPSTREAM PR #21421: mtmd: add Gemma 4 audio conformer encoder support
#1336 opened Apr 6, 2026 by loci-dev Loading…
9 tasks done
2
UPSTREAM PR #21216: common : simplify autoparser tagged parser rules
#1335 opened Apr 6, 2026 by loci-dev Loading…
1
ProTip! Mix and match filters to narrow down what you’re looking for.