Skip to content
This repository has been archived by the owner on Aug 30, 2024. It is now read-only.

Issues: intel/neural-speed

19 Open 28 Closed
19 Open 28 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

Once upon a time, a little NE_ASSERT: /root/w0/workspace/neuralspeed-wheel-build/nlp_repo/neural_speed/core/ne_layers.c:2651: ne_nelements(a) == ne0 * ne1 * ne2
#326 opened Aug 26, 2024 by zwx109473
2
BF16 Compute DType on AVX512 ISA
#308 opened Jul 4, 2024 by Alavandar08
Whats the different with IPEX-LLM?
#290 opened Jun 13, 2024 by manfye
Bestla Kernels understanding and benchmarking
#289 opened Jun 11, 2024 by Alavandar08
8
developer_document.md need elaboration on determining buffer sizes?
#287 opened Jun 9, 2024 by hpcpony
1
Performance on Xeon Scalable
#284 opened Jun 5, 2024 by regmibijay
1
Add support for phi3-vision
#268 opened May 25, 2024 by bil-ash
@intellinjun
1
source build from release tar file?
#258 opened May 19, 2024 by hpcpony
@zhentaoyu
1
Loading checkpoint shards takes too long
#251 opened May 9, 2024 by irjawais
@intellinjun
2
i saw how beautiful this repo is, in terms of parallelism / numa stuff etc.
#231 opened Apr 24, 2024 by kolinfluence
1
i wish for simpler way to run the model
#230 opened Apr 23, 2024 by kolinfluence
@a32543254
4
Garbled characters with beam search
#215 opened Apr 12, 2024 by jiafuzha
@a32543254 @zhentaoyu
16
Distributing tensors across NUMA nodes
#207 opened Apr 6, 2024 by shg8
@kevinintel
3
Running Q4_K_M gguf models: unrecognized tensor type 12
#206 opened Apr 6, 2024 by shg8
@Zhenzhong1
1
Feature request: JSON mode output
#204 opened Apr 5, 2024 by eliranwong
@kevinintel
1
AssertionError: Fail to convert pytorch model
#194 opened Mar 27, 2024 by anthony-intel
@zhentaoyu
3
Neural Speed compilation failing in ORT
#188 opened Mar 22, 2024 by sunnyshu-intel
3
Performance Gap between Neural Speed Matmul Operator and Llama.cpp Operator enhancement New feature or request
#174 opened Mar 13, 2024 by aciddelgado
@luoyu-intel
13
Modifying the models hyperparameters
#124 opened Feb 16, 2024 by benjamin27315k
@Zhenzhong1
8
ProTip! Follow long discussions with comments:>50.