Create devcontainer.json #189
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Fix HTTP to HTTPS for Hugging Face blog link - Fix Groq blog link: HTTP to HTTPS, add /blog/ path, fix typo (open-model → open-models) - Fix TensorRT-LLM documentation filename (blog_9 to blog9)
Try fix pypi ci
Fix another extra "= messages" in README
Corrected several typos and updated all references from 'Pytorch' to 'PyTorch' for consistency. Improved clarity in model descriptions and usage instructions throughout the README.
The project had almost no test coverage - just a single test checking if the API returns 200. This adds proper testing infrastructure and 21 new tests covering the main API functionality. Tests now cover response creation, error handling, tools, sessions, performance, and usage tracking. All tests passing.
It was previously pointing to an empty __init__.py. Also remove unused date import.
Add links to relevant AMD resources
* Correct small grammar issues for better comprehension * Update README.md --------- Co-authored-by: Christopher Whitelam <[email protected]> Co-authored-by: Dominik Kundel <[email protected]>
- Fix OpenAI Cookbook NVIDIA article URL (remove incorrect gpt-oss/ prefix) - Fix Groq Responses API documentation URL (responses → responses-api)
used a specific plataform accepted by pypl
…ion (openai#27) * Update wheel configuration in pyproject.toml to include package tree * Added python dependency and shell globbing for metal command
* evals: admit --sampler chat_completions * gpt_oss.evals: allow modifying the model names
Move activation buffers from Model to Context, so they are no longer shared across contexts and multiple contexts can sample in parallel
- Put quotes around `pip -e` args - Use `hf` over `huggingface-cli` (deprecated)
* Update attention kernel to use TensorDescriptor Block pointer is deprecated in triton, so replacing with the TensorDescriptor API which also enables use of TMA hardware on hopper and newer GPUs. * Add minimum triton version
* Update awesome-gpt-oss.md * Update awesome-gpt-oss.md * Update awesome-gpt-oss.md --------- Co-authored-by: Dominik Kundel <[email protected]>
* add uv python backend Co-authored-by: simon-mo <[email protected]> * dangerously_use_uv --------- Co-authored-by: simon-mo <[email protected]>
Codebase works fine with CPython 3.13, and the current stable is 3.13.7, so no good reason to restrict that
* Update awesome-gpt-oss.md * Update awesome-gpt-oss.md * Update awesome-gpt-oss.md * Add Lemonade to AMD section --------- Co-authored-by: Dominik Kundel <[email protected]>
2% speedup on gpt-oss-20b end-to-end sampling
* Add You.com as tool for browser * change key name * update tests in order to mock API key * address changes * address changes * update README
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.