Chunxiang Xu avadesian
Loading Heatmap…

avadesian synced commits to spot-hedge at avadesian/skypilot from mirror

1 day ago

avadesian synced commits to master at avadesian/skypilot from mirror

  • 118fc79b98 [k8s] Remove privileged container requirement to support GPU isolation (#3443) * Add fuse device manager * Add resource field for checking fuse requirement * lint * lint * lint * lint * lint * comments * lint * fix * fix * fix backward compat * add comment
  • 281e4891db Allow uppercase letters in task names (#3453) The error message specifically states that upper case letters are allowed, but the regex previously did not allow them.
  • 6eb1d97add [LLM] Minor fix for Llama-3 readme (#3452) * minor fix for readme * smaller logo
  • 24fcb44e70 [LLM] Add docs for serving Llama3 (#3449) * Add scripts for llama-3 * use vllm release instead of github * Fix llama3 readme and yaml * Add gallery * Add accelerators for 8B * fix gui.yaml * fix comments * Add options for 8B in yaml * use fastchat gradio instead for better prompt * version for fastchat * fix --register * add flash attn * Fix guis * Fix installation * fix chat template * fix demo * ADD NEW * Update llm/llama-3/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Update llm/llama-3/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * address comments * address comments * fix title * Add logo * fix logo * fix * smaller logo * smaller * minor --------- Co-authored-by: Zongheng Yang <zongheng.y@gmail.com>
  • cade827c53 [Core][BugFix] Fix docker runtime env on Azure (#3450) * fix * format
  • Compare 5 commits »

1 day ago

avadesian synced commits to llama3 at avadesian/skypilot from mirror

1 day ago

avadesian synced commits to fix-docker-gpu at avadesian/skypilot from mirror

  • dbad5dbfe1 Merge remote-tracking branch 'origin/master' into fix-docker-gpu
  • 281e4891db Allow uppercase letters in task names (#3453) The error message specifically states that upper case letters are allowed, but the regex previously did not allow them.
  • 6eb1d97add [LLM] Minor fix for Llama-3 readme (#3452) * minor fix for readme * smaller logo
  • 24fcb44e70 [LLM] Add docs for serving Llama3 (#3449) * Add scripts for llama-3 * use vllm release instead of github * Fix llama3 readme and yaml * Add gallery * Add accelerators for 8B * fix gui.yaml * fix comments * Add options for 8B in yaml * use fastchat gradio instead for better prompt * version for fastchat * fix --register * add flash attn * Fix guis * Fix installation * fix chat template * fix demo * ADD NEW * Update llm/llama-3/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Update llm/llama-3/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * address comments * address comments * fix title * Add logo * fix logo * fix * smaller logo * smaller * minor --------- Co-authored-by: Zongheng Yang <zongheng.y@gmail.com>
  • cade827c53 [Core][BugFix] Fix docker runtime env on Azure (#3450) * fix * format
  • Compare 12 commits »

1 day ago

avadesian synced commits to main at avadesian/Vicuna from mirror

4 days ago

avadesian synced commits to master at avadesian/skypilot from mirror

  • 20493fb616 Quick error handling fix (#3447) syntax fix

4 days ago

avadesian synced commits to fix-docker-gpu at avadesian/skypilot from mirror

4 days ago

avadesian synced commits to fix-controller-cloud at avadesian/skypilot from mirror

  • c8319b634f Merge remote-tracking branch 'origin/master' into fix-controller-cloud
  • c9f575cf3d better nc error message on mac (#3374) * initial commit * newline * comments * run linter * reminder for down * tentatively done with example * formatting * yapf * [Storage] Storage mounting tool permissions fix (#3215) * fix permissions * fix permissions * [LLM] Example for Serving Gemma (#3207) * Add serve for gemma and fix mixtral dependency * Add hf token * fix model len * Add comment * Serve your private gemma * fix serve yaml * readme * Remove chat completion due to the wrong template * add readme * Update llm/gemma/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * address comments * Update README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Update llm/gemma/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Update llm/gemma/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Update llm/gemma/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Change to it * Add chat API * use HF_TOKEN env * typo --------- Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * [LLM] Add logo for Gemma (#3220) * Minor fixes for release 0.5.0 (#3212) * when removing cudo credential, sky check fails * remove tips * minor hint fix * fix cluster version for k8s * fix typo * [Docker] Add retry for docker pull due to daemon not ready (#3218) * Add retry for docker pull due to daemon not ready * longer wait time * longer wait time * retry earlier * add retry for retries as well * longer wait time * change wait time * format * Add comment * Fix * Fix indent for azure docker config * Fix docker login config * Fix comments * More robust docker login config * Add retry for docker check * minor fix * Add additional test for stop and start with docker * Fix cancelled * added comments * quick fix * finished pip issues * fix * fix storage error message, add example link to docs * changed error message if default nc installed on mac * refactored check_port_forward_mode_dependencies function * update comment --------- Co-authored-by: Sheth <shethhriday29@berkeley.edu> Co-authored-by: Romil Bhardwaj <romil.bhardwaj@berkeley.edu> Co-authored-by: Zhanghao Wu <zhanghao.wu@outlook.com> Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> Co-authored-by: Romil Bhardwaj <romil.bhardwaj@gmail.com>
  • 91d6d1bb54 [Core] Add ~/.local/bin to make `which ray` work if ray is installed in `~/.local` (#3368) * save ray path * only use path in file when non empty * try grepping but fail * hardcode ~/.local/bin * format * add comments * Add comments * format * avoid backward compat test conflict * fix sleep * Fix the task ID for spot pipeline
  • e60eb73642 [Spot] Refactor spot APIs into `spot.xxx` (#3417) * Refactor spot core APIs to `sky.spot.core` * Add comment * fix * format * change to spot_lib instead * Update sky/spot/core.py Co-authored-by: Tian Xia <cblmemo@gmail.com> * address comments * Add deprecation message * fix * format * minor fix for backward compat test * longer time * longer wait for spot backward test * fix --------- Co-authored-by: Tian Xia <cblmemo@gmail.com>
  • 226c1eb094 [AI Gallery] Add quantized LLMs with Ollama (#3422) * WIP * arm64 support * wip * wip * add ollama to ai gallery * minor edits * minor edits * Updates * comments * Add 'new' tag
  • Compare 13 commits »

4 days ago

avadesian synced commits to master at avadesian/skypilot from mirror

  • c9f575cf3d better nc error message on mac (#3374) * initial commit * newline * comments * run linter * reminder for down * tentatively done with example * formatting * yapf * [Storage] Storage mounting tool permissions fix (#3215) * fix permissions * fix permissions * [LLM] Example for Serving Gemma (#3207) * Add serve for gemma and fix mixtral dependency * Add hf token * fix model len * Add comment * Serve your private gemma * fix serve yaml * readme * Remove chat completion due to the wrong template * add readme * Update llm/gemma/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * address comments * Update README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Update llm/gemma/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Update llm/gemma/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Update llm/gemma/README.md Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * Change to it * Add chat API * use HF_TOKEN env * typo --------- Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> * [LLM] Add logo for Gemma (#3220) * Minor fixes for release 0.5.0 (#3212) * when removing cudo credential, sky check fails * remove tips * minor hint fix * fix cluster version for k8s * fix typo * [Docker] Add retry for docker pull due to daemon not ready (#3218) * Add retry for docker pull due to daemon not ready * longer wait time * longer wait time * retry earlier * add retry for retries as well * longer wait time * change wait time * format * Add comment * Fix * Fix indent for azure docker config * Fix docker login config * Fix comments * More robust docker login config * Add retry for docker check * minor fix * Add additional test for stop and start with docker * Fix cancelled * added comments * quick fix * finished pip issues * fix * fix storage error message, add example link to docs * changed error message if default nc installed on mac * refactored check_port_forward_mode_dependencies function * update comment --------- Co-authored-by: Sheth <shethhriday29@berkeley.edu> Co-authored-by: Romil Bhardwaj <romil.bhardwaj@berkeley.edu> Co-authored-by: Zhanghao Wu <zhanghao.wu@outlook.com> Co-authored-by: Zongheng Yang <zongheng.y@gmail.com> Co-authored-by: Romil Bhardwaj <romil.bhardwaj@gmail.com>
  • 91d6d1bb54 [Core] Add ~/.local/bin to make `which ray` work if ray is installed in `~/.local` (#3368) * save ray path * only use path in file when non empty * try grepping but fail * hardcode ~/.local/bin * format * add comments * Add comments * format * avoid backward compat test conflict * fix sleep * Fix the task ID for spot pipeline
  • Compare 2 commits »

5 days ago

avadesian synced commits to main at avadesian/guidance from mirror

  • e18be92f53 Update README.md
  • 5c9776e0ae First stab at minimal mypy implementation (#738) Issue: https://github.com/guidance-ai/guidance/issues/729 https://github.com/guidance-ai/guidance/issues/257 - **Set up the structure of mypy installs, now to start typing things** - **fixed guidance/library/_regex.py:13: SyntaxWarning: invalid escape sequence '\['** - **First stab at minimal mypy implementation** This is a non-strict implementation of mypy, with cicd integrated. After this is approved, we can either slowly move towards a strict implementation, or each PR can simply choose how much they want/need to contribute to the typing system to help themselves understand the codebase.
  • c366498702 Generation with `pydantic` schemas (#724) This PR adapts some previous work by @riedgar-ms to enable generating valid JSON given a pydantic model.
  • 03d2b978df [Test] Expand testing of substring() (#751) The `substring()` function wasn't being tested in the builds. Make the following changes: - Add a `name` argument to `substring()` so we can extract the parts we need - Tweak the existing test, so that it is not skipped - Add several tests using the `Mock` which should capture the various automaton states in `substring()`
  • 8a34f7a054 Merge pull request #750 from riedgar-ms/riedgar-ms/extra-docs-01 [Docs] Expand documentation
  • Compare 13 commits »

5 days ago

avadesian synced commits to operation at avadesian/Vicuna from mirror

1 week ago

avadesian synced commits to main at avadesian/Vicuna from mirror

1 week ago

avadesian synced commits to spot-hedge at avadesian/skypilot from mirror

1 week ago

avadesian synced commits to serve_k8s_playground at avadesian/skypilot from mirror

1 week ago

avadesian synced commits to ray_path at avadesian/skypilot from mirror

1 week ago

avadesian synced commits to main at avadesian/Vicuna from mirror

1 week ago

avadesian synced commits to serve_k8s_final at avadesian/skypilot from mirror

1 week ago

avadesian synced commits to master at avadesian/skypilot from mirror

  • e60eb73642 [Spot] Refactor spot APIs into `spot.xxx` (#3417) * Refactor spot core APIs to `sky.spot.core` * Add comment * fix * format * change to spot_lib instead * Update sky/spot/core.py Co-authored-by: Tian Xia <cblmemo@gmail.com> * address comments * Add deprecation message * fix * format * minor fix for backward compat test * longer time * longer wait for spot backward test * fix --------- Co-authored-by: Tian Xia <cblmemo@gmail.com>
  • 226c1eb094 [AI Gallery] Add quantized LLMs with Ollama (#3422) * WIP * arm64 support * wip * wip * add ollama to ai gallery * minor edits * minor edits * Updates * comments * Add 'new' tag
  • Compare 2 commits »

1 week ago

avadesian synced commits to spot-refactor at avadesian/skypilot from mirror

1 week ago

avadesian synced commits to serve_k8s_playground at avadesian/skypilot from mirror

1 week ago