Skip to content

Issues: ggerganov/ggml

ggml : unified file format
#220 by philpax was closed Nov 1, 2023
Closed 82
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

Clear current search query, filters, and sorts
217 Open 170 Closed
217 Open 170 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

Sparsity - The next performance frontier.
#93 opened Apr 19, 2023 by JohnnyOpcode updated May 23, 2023
2
Support CodeT5+
#192 opened May 23, 2023 by s-kostyaev updated May 23, 2023
Getting error on make -j4 gpt-2
#45 opened Mar 22, 2023 by praveenkumar91 updated May 24, 2023
1
[Feature Request] Support PyTorch GPT-2 Models
#76 opened Apr 10, 2023 by nomyTx updated May 25, 2023
1
torch model to ggml
#149 opened May 11, 2023 by sadik-abd updated May 27, 2023
4
clBLAST Compile fails due to recent changes.
#205 opened May 28, 2023 by apcameron updated May 28, 2023
Add library function to estimate size of computation graph work tensor enhancement New feature or request
#214 opened May 30, 2023 by LoganDark updated May 30, 2023
@ggerganov
1
CUDA error 35 at ggml-cuda.cu:452: CUDA driver version is insufficient for CUDA runtime version
#226 opened Jun 3, 2023 by dynamite9999 updated Jun 3, 2023
slow inference with very long input embeddings
#49 opened Mar 26, 2023 by nikisalli updated Jun 3, 2023
2
GPTNeoX model with 16k context results in context-size related issues: ggml_new_tensor_impl: not enough space in the context's memory pool, and instant core dump with fp16
#225 opened Jun 3, 2023 by TheBloke updated Jun 4, 2023
2
common.cpp printf() formats for [u]int64_t and size_t warnings
#243 opened Jun 10, 2023 by leok7v updated Jun 10, 2023
model unloads from memory after latest update
#245 opened Jun 11, 2023 by aseok updated Jun 11, 2023
Build on Windows build build related issues
#19 opened Jan 19, 2023 by LaOrhyUAcMji updated Jun 13, 2023
4
Illegal instruction (CPU feature misdetection)
#258 opened Jun 14, 2023 by MostAwesomeDude updated Jun 15, 2023
1
Support AlphaFold2
#265 opened Jun 17, 2023 by martin-steinegger updated Jun 17, 2023
What is the relationship between the number of CPU cores and the speedup?
#232 opened Jun 6, 2023 by kohlerm updated Jun 18, 2023
2
don't print in ggml_init_cublas
#271 opened Jun 20, 2023 by LoganDark updated Jun 20, 2023
1
Does ggml support onnx format model as input ?
#273 opened Jun 21, 2023 by lix19937 updated Jun 21, 2023
cmake fails without -G
#211 opened May 29, 2023 by NancyAurum updated Jun 21, 2023
1
Partially forward cgraph
#283 opened Jun 24, 2023 by LoganDark updated Jun 24, 2023
1
Validation issue in test-mul-mat0c.
#306 opened Jun 26, 2023 by kant2002 updated Jun 26, 2023
Need RedPajama-3b support
#304 opened Jun 26, 2023 by madroidmaq updated Jun 26, 2023
1
Can GGML apply in CNN or RCNN ?
#208 opened May 29, 2023 by znsoftm updated Jun 26, 2023
2
convert fine tuned model to ggml?
#280 opened Jun 23, 2023 by silvacarl2 updated Jun 27, 2023
4
[Documentation] How to quantize using ggml?
#320 opened Jun 28, 2023 by mahimairaja updated Jun 28, 2023
ProTip! Follow long discussions with comments:>50.