Skip to content

Issues: ggerganov/llama.cpp

examples : add configuration presets
#10932 opened Dec 21, 2024 by ggerganov
Open 3
changelog : libllama API
#9289 opened Sep 3, 2024 by ggerganov
Open 5
changelog : llama-server REST API
#9291 opened Sep 3, 2024 by ggerganov
Open 12
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

273 Open 4,095 Closed
273 Open 4,095 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Compile bug: c++cc: : error: error: unsupported argument 'native+nodotprod+noi8mm+nosve' to option '-mcpu='unsupported argument 'native+nodotprod+noi8mm+nosve' to option '-mcpu=' bug-unconfirmed
#11428 opened Jan 26, 2025 by anyuser201
Feature Request: SwiftKV support (~2x performance boost) enhancement New feature or request
#11415 opened Jan 25, 2025 by coder543
4 tasks done
Feature Request: Is it possible to support kosmos-2.5? enhancement New feature or request
#11413 opened Jan 25, 2025 by gnusupport
4 tasks done
Feature Request: Make customizable the name of assistant on web UI enhancement New feature or request
#11412 opened Jan 25, 2025 by gnusupport
4 tasks done
Misc. bug: connection reset by peer for some initial requests when concurrent request llama-server embedding endpoint bug-unconfirmed
#11411 opened Jan 25, 2025 by zwpaper
Compile bug: compiling llama.cpp against CUDA 12 succeeds but resulting binaries cannot find shared libraries bug-unconfirmed
#11404 opened Jan 25, 2025 by compilebunny
3
Misc. bug: jinja template with exception ruins the template bug-unconfirmed
#11402 opened Jan 24, 2025 by drazdra
Misc. bug: changes to template processing crash llama.cpp instead of falling back to old template processing when template is not supported bug-unconfirmed
#11400 opened Jan 24, 2025 by drazdra
Eval bug: is it possible to support SmolVLM-500M-Instruct? bug-unconfirmed
#11387 opened Jan 24, 2025 by gnusupport
Compile bug: llama.cpp-master/ggml/src/ggml-cpu/ggml-cpu-aarch64.cpp:80:54:error '_mm256_set_m128i' was not declared in this scope bug-unconfirmed
#11385 opened Jan 24, 2025 by zhangyangniubi
Eval bug: Slow model loading w/ mmap bug-unconfirmed
#11382 opened Jan 24, 2025 by hg0428
DeepSeek-R1-Zero-GGUF fails with src/llama.cpp:5142: GGML_ASSERT(hparams.n_expert <= LLAMA_MAX_EXPERTS) failed bug-unconfirmed
#11378 opened Jan 23, 2025 by quarterturn
1
Compile bug: No rule to make target '/usr/lib/librt.a' bug-unconfirmed
#11376 opened Jan 23, 2025 by jiafatom
1
Eval bug: Error running multiple contexts from multiple threads at the same time with Vulkan bug-unconfirmed
#11371 opened Jan 23, 2025 by charlesrwest
Eval bug: No layers are offloaded to the Vulkan GPU bug-unconfirmed
#11367 opened Jan 23, 2025 by yurivict
3
Eval bug: very slow inference on DeepSeek-R1-Distill-Qwen-32B bug-unconfirmed
#11361 opened Jan 22, 2025 by lexasub
6
Feature Request: reasoning_effort parameter for reasoning models like R1 enhancement New feature or request
#11351 opened Jan 22, 2025 by zakkor
4 tasks done
4
Misc. bug: Failed to convert MiniCPM-o-2_6 bug-unconfirmed
#11347 opened Jan 22, 2025 by apepkuss
Eval bug: Issue when trying to run exaone model after hf to gguf conversion bug-unconfirmed
#11345 opened Jan 22, 2025 by Zhaeong
Misc. bug: Deepseek R1 incompatible with grammars / structured output bug-unconfirmed
#11336 opened Jan 21, 2025 by noahhaon
4
Eval bug: llama-server stopped working after PR #11285 got merged bug-unconfirmed
#11335 opened Jan 21, 2025 by tim-janik
@ngxson
7
Feature Request: NUMA-aware MoE Expert Allocation for Improved Performanc enhancement New feature or request
#11333 opened Jan 21, 2025 by l15y
1
Eval bug: ggml_gallocr_reserve_n tries to allocate beyond max buffer size bug-unconfirmed
#11332 opened Jan 21, 2025 by BenPortner
9
Compile bug: Vulkan can not work on Android (cross-compilation from linux) - Aborted without explaination bug-unconfirmed
#11327 opened Jan 21, 2025 by samkoesnadi
27
Eval bug: <think> tag with DeepSeek-R1-Distill-Qwen-1.5B-Q5_K_M.gguf bug-unconfirmed
#11325 opened Jan 21, 2025 by gnusupport
16
ProTip! Adding no:label will show everything without a label.