Skip to content

Pull requests: ikawrakow/ik_llama.cpp

New pull request New
26 Open 1,330 Closed
26 Open 1,330 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

GLM DSA: reduce indexer cache size
#2093 opened Jul 6, 2026 by ikawrakow Owner Loading…
Be able to force synchronization when copying graph ginputs
#2092 opened Jul 6, 2026 by ikawrakow Owner Loading…
1
GLM-DSA: do not compute indexer score if context < n_top_k
#2090 opened Jul 6, 2026 by ikawrakow Owner Loading…
feat: Add MiniMax M3 Vision Projector Support
#2086 opened Jul 5, 2026 by jkyamog Contributor • Draft
2
fix: MiniMax-M3 streaming parser when tool calls start before </mm:think>
#2085 opened Jul 5, 2026 by jkyamog Contributor • Draft
1
model: add openPangu-2.0-Flash (92B-A6B) with MLA-latent cache, DSA/SWA, and NextN MTP
#2065 opened Jul 2, 2026 by joelfarthing Contributor • Draft
2 of 4 tasks
13
Bound DFlash SWA K/V cache to the sliding window
#2064 opened Jul 1, 2026 by SamuelOliveirads Collaborator Loading…
7
Parallelize weight loading for weights targeted at anonymous host ram and also GPU
#2057 opened Jun 29, 2026 by Farmadupe Contributor Loading…
2 tasks done
8
add --split-output-tensor / -sot CLI parameter
#2056 opened Jun 29, 2026 by Nexesenex Contributor • Draft
2 of 4 tasks
2
implement perplexity in llama-server
#2011 opened Jun 22, 2026 by magikRUKKOLA Contributor • Draft
2
fix: checkpoint restore for hybrid/recurrent models
#1976 opened Jun 16, 2026 by razlani Loading…
1
5
delta-net: fix np>1 hybrid recurrent-state corruption (batched multi-seq)
#1933 opened Jun 7, 2026 by poisonxa16 Loading…
9
Fix misc. expiring logit/sparam bias bugs
#1914 opened Jun 2, 2026 by dungquixote42 Contributor Loading…
2 of 4 tasks
6
Qwen3.5 MTP: extract selected tokens earlier
#1892 opened May 28, 2026 by ikawrakow Owner Loading…
server: enable checkpoint reuse for recurrent/hybrid models (qwen3next, Mamba)
#1888 opened May 26, 2026 by localweights Loading…
1
3
Fix prompt cache viability
#1877 opened May 25, 2026 by zeljkokalezic Loading…
2 of 4 tasks
5
docs: Complete rewrite of build.md – CMake-only, focused on supported backends
#1853 opened May 21, 2026 by maddes8cht Loading…
2 of 4 tasks
76
A GGUF MTP Extract and Merge Tool
#1849 opened May 20, 2026 by FNsi • Draft
2 of 4 tasks
2
cuda: add get_rows CUDA kernels for Q4_K, Q5_K, Q6_K
#1830 opened May 18, 2026 by localweights Loading…
5
Slightly expand the usage of VNNI256
#1764 opened May 9, 2026 by XZiar Contributor Loading…
2 of 4 tasks
1
A GGUF editor, which can be use to duplicate or delete layers in Qwen3.5 / Qwen Coder Next or whatever but may not run in 1 shot.
#1746 opened May 6, 2026 by FNsi • Draft
1 of 3 tasks
14
runtime : add --run-time-repack auto mode for swap-bound MoE safety
#1738 opened May 4, 2026 by AndrewMoryakov Contributor Loading…
2 of 4 tasks
9
Change signature of llama_set_draft_input_hidden_state
#1727 opened May 3, 2026 by ikawrakow Owner Loading…
3
convert_hf_to_gguf: add Qwen3.5 / Qwen3.6 support (+ Qwen3-Next scaffolding, not e2e-verified)
#1654 opened Apr 18, 2026 by markaalonzo Contributor • Draft
18
Add reuse property to ggml_cgraph
#1617 opened Apr 11, 2026 by ikawrakow Owner Loading…
4
ProTip! Adding no:label will show everything without a label.