-
Notifications
You must be signed in to change notification settings - Fork 1
Pull requests: auroralabs-loci/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
UPSTREAM PR #19581: cmake: fix KleidiAI install target failure with EXCLUDE_FROM_ALL
#1174
opened Feb 13, 2026 by
loci-dev
Loading…
UPSTREAM PR #19575: ggml-cpu: arm64: Fix wrong memcpy length for q4_K block_interleave == 4
#1173
opened Feb 13, 2026 by
loci-dev
Loading…
UPSTREAM PR #19572: server: add Anthropic-compatible
cache_read_input_tokens to usage metrics
#1172
opened Feb 13, 2026 by
loci-dev
Loading…
1 task done
UPSTREAM PR #19551: (webui) REFACTOR: UI primitives and polish
#1171
opened Feb 12, 2026 by
loci-dev
Loading…
UPSTREAM PR #19540: scripts : add support for forks in pr2wt.sh
#1169
opened Feb 12, 2026 by
loci-dev
Loading…
UPSTREAM PR #19488: model: add JAIS-2 architecture support
#1168
opened Feb 12, 2026 by
loci-dev
Loading…
UPSTREAM PR #18862: llama : remove write/read of output ids/logits/embeddings
#1167
opened Feb 12, 2026 by
loci-dev
Loading…
UPSTREAM PR #19531: Kimi Linear (correct conv state update + block implementation)
#1165
opened Feb 12, 2026 by
loci-dev
Loading…
UPSTREAM PR #19460: model: support GLM MoE DSA arch (NOTE: indexer is not yet supported)
#1164
opened Feb 12, 2026 by
loci-dev
Loading…
UPSTREAM PR #19493: server : speculative checkpointing
#1163
opened Feb 11, 2026 by
loci-dev
Loading…
UPSTREAM PR #19495: jinja: add missing tojson filter for undefined type
#1162
opened Feb 11, 2026 by
loci-dev
Loading…
UPSTREAM PR #19315: [WebGPU] Plug memory leaks and free resources on shutdown
#1161
opened Feb 10, 2026 by
loci-dev
Loading…
UPSTREAM PR #19433: Add a build target to generate ROCm artifacts using ROCm 7.2
#1160
opened Feb 9, 2026 by
loci-dev
Loading…
UPSTREAM PR #19378: ggml: backend-agnostic tensor parallelism
#1159
opened Feb 8, 2026 by
loci-dev
Loading…
UPSTREAM PR #19317: cleanup
llama-quantize --help output
#1158
opened Feb 8, 2026 by
loci-dev
Loading…
UPSTREAM PR #19406: hexagon: Add ARGSORT, DIV, SQR, SQRT, SUM_ROWS, GEGLU
#1157
opened Feb 7, 2026 by
loci-dev
Loading…
UPSTREAM PR #17791: ggml-cpu: add repack GEMM and GEMV for floating-point
#1155
opened Feb 6, 2026 by
loci-dev
Loading…
UPSTREAM PR #18698: Improving inference speed for the repack buffer type on NUMA architectures
#1154
opened Feb 5, 2026 by
loci-dev
Loading…
UPSTREAM PR #19306: sycl: add F16 support for GGML_OP_CEIL
#1153
opened Feb 4, 2026 by
loci-dev
Loading…
UPSTREAM PR #19288: ggml-cpu: use LUT for converting e8->f32 scales on x86
#1152
opened Feb 3, 2026 by
loci-dev
Loading…
UPSTREAM PR #19286: completion : simplify batch (embd) processing
#1151
opened Feb 3, 2026 by
loci-dev
Loading…
Previous Next
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.