8 Pull requests merged by 4 people

• Update sever README build/testing instructions

  #461 merged Jun 1, 2024

• Upgrade to Cosmopolitan v3.3.10

  #460 merged Jun 1, 2024

• Performance improvements on Arm for legacy and k-quants

  #453 merged May 30, 2024

• github: delete question in favor of link to discussion

  #457 merged May 29, 2024

• github: add ci

  #454 merged May 29, 2024

• github: add mention of strace and ftrace

  #449 merged May 26, 2024

• actions: add labeler + editorconfig github actions

  #443 merged May 26, 2024

• github: delete assignees and about --> description

  #448 merged May 26, 2024

1 Pull request opened by 1 person

• Run clang-format

  #462 opened Jun 1, 2024

3 Issues closed by 3 people

• get_amd_offload_arch_flag: warning: hipInfo output didn't list any graphics cards

  #446 closed Jun 1, 2024

• llama_sampling_init: failed to parse grammar

  #458 closed May 29, 2024

• Are embeddings not supported with the mistral-7b-instruct-v0.2 model?

  #414 closed May 28, 2024

2 Issues opened by 2 people

• Hugging face repository does not show the version of the llamafile you are downloading

  #459 opened May 29, 2024

• instruct chat templates

  #451 opened May 26, 2024

6 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• AMD - tinyBLAS windows prebuilt support stopped working with 0.8.5

  #441 commented on May 28, 2024 • 4 new comments

• Added the ability to use LLAMA_HIP_UMA

  #439 commented on May 26, 2024 • 2 new comments

• Support for whisper.cpp

  #17 commented on May 27, 2024 • 2 new comments

• Windows 10 GPU support bug

  #440 commented on May 27, 2024 • 1 new comment

• Release page 0.6.2 has broken links for "Other Models"

  #237 commented on May 28, 2024 • 1 new comment

• Security

  #15 commented on May 29, 2024 • 1 new comment