Skip to content

Pull requests: ikawrakow/ik_llama.cpp

New pull request New
43 Open 1,515 Closed
43 Open 1,515 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

NUMA Mirror implementation
#2396 opened Aug 31, 2026 by SamuelOliveirads Collaborator Loading…
14
docs: --cache-ram-similarity is a minimum, not a maximum
#2395 opened Aug 31, 2026 by mattafaak Loading…
1
Remove usless check in llama-quantize
#2394 opened Aug 31, 2026 by ikawrakow Owner Loading…
Support SWA compression with DFlash/DSpark
#2384 opened Aug 30, 2026 by SamuelOliveirads Collaborator Loading…
1
server : add --sleep-idle-seconds to auto-unload model on idle
#2383 opened Aug 29, 2026 by Ahmed-Yaseen99 Loading…
2
model: add LFM2 / LFM2.5 (Liquid AI) runtime + conversion support
#2382 opened Aug 29, 2026 by yoirtbryggffdcfgcbcbcffdbfxx Loading…
2 of 4 tasks
1
gemma4: compacted sliding-window KV cache (--swa-compress)
#2378 opened Aug 29, 2026 by azilber Loading…
2
server: disk KV block cache for cross-process prompt prefix reuse
#2377 opened Aug 29, 2026 by AYwlilwYA Loading…
2
model: Add GLM-5.3-Flash (glm5next) runtime support
#2376 opened Aug 28, 2026 by Skelectric Contributor Loading…
2 of 4 tasks
5
Qwen-3.8-Next op fusions
#2375 opened Aug 28, 2026 by ikawrakow Owner Loading…
1
POC: QSA optimization
#2374 opened Aug 28, 2026 by ikawrakow Owner • Draft
6
Map dense Qwen DFlash back to LLM_ARCH_DFLASH
#2370 opened Aug 28, 2026 by SamuelOliveirads Collaborator Loading…
1
2
qwen4exp: MTP (NextN) self-speculative decoding support
#2369 opened Aug 28, 2026 by jcr211 Loading…
2 of 4 tasks
45
Check if enough shared memory available for MLA on CUDA
#2354 opened Aug 25, 2026 by ikawrakow Owner Loading…
1
1
Dspark confidence method in spec-autotune
#2326 opened Aug 16, 2026 by SamuelOliveirads Collaborator Loading…
5
PR: Transfer ATSInfer Tensor Placement Solver into ik_llama.cpp
#2259 opened Aug 5, 2026 by giveen Loading…
2 of 4 tasks
30
deepseek4: add --dsv4-cache-cpu to keep compressed-attention K caches in host memory
#2239 opened Aug 2, 2026 by nmccrory Loading…
2
deepseek4: fix multi-stream (parallel sequence) decoding
#2229 opened Aug 2, 2026 by nmccrory Loading…
8
window-sized SWA ring KV cache (--swa-compress to opt in)
#2171 opened Jul 23, 2026 by joaomdsg Loading…
38
CUDA sm_60: bound the fp16 flash-attention error on P100 prefill instead of disabling the fast path
#2151 opened Jul 18, 2026 by mb8565 Contributor Loading…
6
ggml : fix build and MoE inference on CPUs without AVX2 (AVX1-only)
#2138 opened Jul 15, 2026 by neomindryan Loading…
2 of 4 tasks
6
llama: disable fused up-gate when an offload backend lacks GGML_OP_FUSED_UP_GATE (fixes silent 3.5x Metal slowdown)
#2133 opened Jul 15, 2026 by hchengit Contributor Loading…
4
Scope split-mode graph mmap to the tensor being loaded. Prevents memory leak
#2126 opened Jul 13, 2026 by Farmadupe Contributor • Draft
2 of 4 tasks
Reduce host memory pressure when performing a sm graph load.
#2125 opened Jul 13, 2026 by Farmadupe Contributor • Draft
1
CUDA: update captured graph when a source tensor's shape changes
#2096 opened Jul 8, 2026 by fibrahimov Loading…
3
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.