Skip to content

Pull requests: ggerganov/llama.cpp

New pull request New
218 Open 2,868 Closed
218 Open 2,868 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

add_special option for server tokenize endpoint
#7059 opened May 3, 2024 by JohanAR Loading…
3
Script to convert Grok-1 weights from raw JAX pickle files.
#7058 opened May 3, 2024 by heiner Loading…
5
BPE pretokenizer - add support for command-r-plus and command-r models
#7041 opened May 2, 2024 by sealad886 Loading…
2
3
Decide pre tokenizer based on preprocessing of entry and not on tokens encoded
#7039 opened May 2, 2024 by JoanFM • Draft
10
Bug fix for server crash if first token is the stop word and asking for logprobs
#7038 opened May 2, 2024 by maor-ps Loading…
1
tests : add test-tokenizer-0.sh
high priority Very important issue
#7036 opened May 2, 2024 by ggerganov Loading…
4
Disable benchmark on forked repo
#7034 opened May 2, 2024 by CISC Loading…
Add BPE pre-tokenization for Command-R.
#7033 opened May 2, 2024 by dranger003 Loading…
1
13
convert-hf : reduce repeated boilerplate from write_tensors
need feedback Testing and feedback with results are needed refactoring Refactoring
#7031 opened May 1, 2024 by compilade Loading…
3 of 18 tasks
11
Add token healing example
#7028 opened May 1, 2024 by mare5x • Draft
1
convert.py: When --vocab-only is passed, generate false but valid params
#7027 opened May 1, 2024 by 20kdc Loading…
5
docs: Fix typo and update description for --embeddings flag
#7026 opened May 1, 2024 by louixs Loading…
2
Added support for the ArcticForCausalLM.
#7020 opened May 1, 2024 by fairydreaming Loading…
1
4
chore: Add hashsum for stablelm models
#7018 opened May 1, 2024 by teleprint-me Loading…
8
Tidy Android Instructions README.md
#7016 opened Apr 30, 2024 by Jeximo Loading…
14
Update Server's README with undocumented options for RoPE, YaRN, and KV cache quantization
#7013 opened Apr 30, 2024 by K-Mistele Loading…
2
Fix flash attention for ROCm
#7011 opened Apr 30, 2024 by jdecourval • Draft
5
add chatglm3-6b model support [help wanted]
#6999 opened Apr 30, 2024 by mnlife • Draft
1
new tokenizer-verifier tool to check gguf tokenizer parameters
#6988 opened Apr 29, 2024 by anisse Loading…
1
Attempt at OpenElm
#6986 opened Apr 29, 2024 by joshcarp • Draft
1
10
llama3 custom regex split
#6965 opened Apr 28, 2024 by jaime-m-p Loading…
16
server: avoid breaking KV cache when prompt >= n_ctx
#6958 opened Apr 28, 2024 by prfd • Draft
7
move ndk code to a new library
#6951 opened Apr 27, 2024 by eltonkola Loading…
Option to split during conversion
#6942 opened Apr 27, 2024 by christianazinn • Draft
11
Updated server_queue to delete tasks from queue when server is shutdown. Feature Request #6421
demo Demonstrate some concept or idea, not intended to be merged
#6941 opened Apr 27, 2024 by rahsuri Loading…
4
ProTip! Add no:assignee to see everything that’s not assigned.