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

207 Open 167 Closed
207 Open 167 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
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

[2GPU] Memcpy2D of matrixXmatrix -- src size (and form)
#590 opened Oct 22, 2023 by kotee4ko
3
Issue with ggml
#588 opened Oct 20, 2023 by grpinto
1
Using memcpy on tensor data when the tensor is not contiguous
#584 opened Oct 17, 2023 by audiovention
1
ggml : create a complete document
#568 opened Oct 10, 2023 by Cyberhan123
5
[Question] What is the status of Vulkan backend?
#542 opened Sep 27, 2023 by DanielMazurkiewicz
12
How about adding "tokenizer.ggml.cls_token_id" for special cls token.
#541 opened Sep 26, 2023 by FFengIll
Issue inferencing HuggingFace's GPT-J 4 bits model
#539 opened Sep 25, 2023 by webpolis
1
[Feature Request] any hyper-resolution inference
#538 opened Sep 25, 2023 by FNsi
2
Is T5 (mLongT5, FlanT5 etc.) being developed with GGML ?
#537 opened Sep 25, 2023 by thusinh1969
1
prompt is too long (539 tokens, max 508)
#536 opened Sep 25, 2023 by muhammadfhadli1453
Can't some operations run in parallel?
#535 opened Sep 23, 2023 by ita9naiwa
1
Merge HF LoRa adapter with a quantized GPT-J model using ggml
#534 opened Sep 23, 2023 by webpolis
Port k-quants support from ggerganov/llama.cpp to ggerganov/ggml
#532 opened Sep 21, 2023 by saharNooby
Asserting over nb[0] as type check causes issue for tensors after permuting
#530 opened Sep 19, 2023 by cndn
1
Why GGML_F16_STEP is 32?
#526 opened Sep 15, 2023 by xshen053
3
Why GPT-J performs better on graviton without using simd than x86 using simd
#520 opened Sep 13, 2023 by xshen053
Converting an arbritrary HF Transformer GPT2 to ggml format
#519 opened Sep 12, 2023 by JellePiepenbrock
1
No output from executable when building with MSYS2
#518 opened Sep 12, 2023 by snunez1
Directly converted from bfloat16 weights are 20x slower than converted from float32 ones.
#516 opened Sep 11, 2023 by OlegJakushkin
How to easily convert Meta's MMS-ASR models to ggml?
#507 opened Sep 6, 2023 by allandclive
1
ggml : better way to express implicit node dependencies in a graph enhancement New feature or request refactoring Refactoring
#502 opened Sep 4, 2023 by ggerganov
mpt-1b fails with mpt_model_load: unknown tensor 'transformer.blocks.0.attn.k_ln.weight' in model file
#499 opened Sep 1, 2023 by OlegJakushkin
4
[Feature request] Add support/demo implementation for Qwen-VL GGUF model
#497 opened Aug 30, 2023 by CoruNethron
2
Use custom GPT-J checkpoint
#488 opened Aug 28, 2023 by mariecwhite
1
gpt-j, starcoder, gptneox examples cause "not enough space in the context's memory pool" for batches >32
#484 opened Aug 27, 2023 by ravenscroftj
2
ProTip! What’s not been updated in a month: updated:<2024-05-18.