Skip to content

Pull requests: ggerganov/llama.cpp

New pull request New
218 Open 2,899 Closed
218 Open 2,899 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 BPE pre-tokenization for DBRX.
#7132 opened May 7, 2024 by dranger003 Loading…
1
1
Fix NFD computation
#7122 opened May 7, 2024 by JoanFM • Draft
2 of 3 tasks
1
chore: Add model vocab support
#7117 opened May 7, 2024 by teleprint-me • Draft
4
Add BPE pre-tokenization for Qwen2.
#7114 opened May 7, 2024 by jklj077 Loading…
3
main : add --conversation / -cnv flag
#7108 opened May 6, 2024 by dawidpotocki Loading…
1
1
tokenization: no double BOS tokens
#7107 opened May 6, 2024 by JohannesGaessler Loading…
11
main-interactive-mode: optionally allow for special tokens from user in interactive mode for fill-in-middle etal
#7097 opened May 6, 2024 by hanishkvc Loading…
1
Documenting debugging one test without anything else in the loop.
#7096 opened May 6, 2024 by josh-ramer Loading…
2
opencl alignment size should be converted from bits to bytes
#7090 opened May 5, 2024 by albertjin Loading…
1
Vulkan Bugfixes and Improvements
#7084 opened May 5, 2024 by 0cc4m Loading…
9
Add left recursion check: quit early instead of going into an infinite loop
#7083 opened May 5, 2024 by nuchi Loading…
1
1
fix: use vm_allocate instead of posix_memalign for Metal on macOS
#7078 opened May 4, 2024 by giladgd Loading…
3
convert-hf : save memory with lazy evaluation
enhancement New feature or request high priority Very important issue need feedback Testing and feedback with results are needed
#7075 opened May 4, 2024 by compilade Loading…
7 tasks done
15
CUDA: generalize FP16 fattn vec kernel
#7061 opened May 3, 2024 by JohannesGaessler Loading…
19
add_special option for server tokenize endpoint
#7059 opened May 3, 2024 by JohanAR Loading…
8
Script to convert Grok-1 weights from raw JAX pickle files.
#7058 opened May 3, 2024 by heiner Loading…
7
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…
11
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
5
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
llama3 custom regex split
#6965 opened Apr 28, 2024 by jaime-m-p Loading…
26
server: avoid breaking KV cache when prompt >= n_ctx
#6958 opened Apr 28, 2024 by prfd Loading…
7
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.