Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
ngxson pushed 1 commit to master ngxson/llama.cpp
- llama : the WPM vocabs use the CLS token as BOS (#10930) * llama : the WPM vocabs use the CLS token as BOS ggml-ci ... 30caac3
ngxson pushed 2 commits to master ngxson/llama.cpp
ngxson pushed 1 commit to master ngxson/llama.cpp
- ggml : fix const usage in SSE path (#10962) 32d6ee6
ngxson created a tag on ngxson/wllama
2.1.1 - WebAssembly binding for llama.cpp - Enabling on-browser LLM inference
ngxson published a release on ngxson/wllama
2.1.1
## What's Changed * sync to latest upstream source code by @ngxson in https://github.com/ngxson/wllama/pull/145 **Full Changelog**: https://github.com/ngxson/wllama/compare/2.1.0...2.1.1
ngxson pushed 1 commit to master ngxson/wllama
- sync to latest upstream source code (#145) * sync to latest upstream source code * tailwind.config.cjs * fix lint 86138c8
ngxson pushed 1 commit to master ngxson/llama.cpp
- server : fix missing model id in /model endpoint (#10957) * server : fix missing model id in /model endpoint * fi... 14b699e
ngxson pushed 1 commit to master ggerganov/llama.cpp
- server : fix missing model id in /model endpoint (#10957) * server : fix missing model id in /model endpoint * fi... 14b699e
ngxson closed an issue on ggerganov/llama.cpp
OpenAI compatible response for /models has empty id and empty name
I have an issue with Open WebUI since b4276 which includes refactor https://github.com/ggerganov/llama.cpp/pull/10643 Now the /api/models returns no id and name for the openai model so the UI cann...
ngxson closed a pull request on ggerganov/llama.cpp
server : fix missing model id in /model endpoint
Fix https://github.com/ggerganov/llama.cpp/issues/10924
ngxson pushed 1 commit to master ngxson/llama.cpp
- server : add system_fingerprint to chat/completion (#10917) * server : add system_fingerprint to chat/completion ... 485dc01
ngxson pushed 1 commit to master ggerganov/llama.cpp
- server : add system_fingerprint to chat/completion (#10917) * server : add system_fingerprint to chat/completion ... 485dc01
ngxson closed a pull request on ggerganov/llama.cpp
server : add system_fingerprint to chat/completion
While working with compatible between llama.cpp and [HF inference library](https://github.com/huggingface/huggingface.js/blob/main/packages/inference/src/tasks/nlp/chatCompletion.ts), I noticed tha...
ngxson opened a pull request on ggerganov/llama.cpp
server : fix missing model id in /model endpoint
Fix https://github.com/ggerganov/llama.cpp/issues/10924
ngxson created a branch on ngxson/llama.cpp
xsn/server_missing_model_id - Forked from ggerganov/llama.cpp
ngxson created a comment on a pull request on ggerganov/llama.cpp
@ggerganov In case you missed, could you please review this PR? Thanks!
ngxson pushed 1 commit to master ngxson/llama.cpp
- rpc-server : add support for the SYCL backend (#10934) 86bf31c
ngxson pushed 3 commits to master ngxson/llama.cpp
- ggml : fix run-time on FreeBSD in get_executable_path() (#10948) 7024d59
- llama-run : include temperature option (#10899) This commit updates the `examples/run/README.md` file to include a n... dab76c9
- llama : support for Llama-3_1-Nemotron-51B (#10669) * conflict resolution * move comments after bracket to its ow... 6f0c9e0
ngxson pushed 2 commits to master ngxson/llama.cpp
ngxson pushed 1 commit to master ggerganov/llama.cpp
- devops : add docker-multi-stage builds (#10832) 7c0e285
ngxson closed a pull request on ggerganov/llama.cpp
added docker-multi-stage builds
Added multi-stage dockerfile builds, improved total build time to under 2 hours, added Vulkan and Full-intel. Updated rocm dockerfile. Hopefully it will all work without any problems.
ngxson created a review on a pull request on ggerganov/llama.cpp
Working as expected now, thanks. Side note, this change may affect users who rely on the old Dockerfile to specifically build server or cli (cmake with `--target`). In case someone ask, we will ...
ngxson created a review comment on a pull request on ggerganov/llama.cpp
> If there is no field, return an empty json for that field. Could you explain what does this mean? Please give an example if possible.