Permalink
Checking mergeability…
Don’t worry, you can still create the pull request.
Comparing changes
Choose two branches to see what’s changed or to start a new pull request.
If you need to, you can also or
learn more about diff comparisons.
Open a pull request
Create a new pull request by comparing changes across two branches. If you need to, you can also .
Learn more about diff comparisons here.
...
- 17 commits
- 252 files changed
- 19 contributors
Commits on Apr 16, 2025
-
-
Add example of DeepCompile (deepspeedai#967)
* import files for deepcompile benchmark Signed-off-by: Masahiro Tanaka <[email protected]> * add figures Signed-off-by: Masahiro Tanaka <[email protected]> * add figures Signed-off-by: Masahiro Tanaka <[email protected]> * update document Signed-off-by: Masahiro Tanaka <[email protected]> * fix links to images Signed-off-by: Masahiro Tanaka <[email protected]> * add images Signed-off-by: Masahiro Tanaka <[email protected]> * specify deepspeed version Signed-off-by: Masahiro Tanaka <[email protected]> --------- Signed-off-by: Masahiro Tanaka <[email protected]> Co-authored-by: Olatunji Ruwase <[email protected]>
Commits on Apr 17, 2025
Commits on Apr 18, 2025
-
Update description of versions for deepcompile (deepspeedai#971)
* update description of versions for deepcompile * Update to match specific tag name Signed-off-by: Logan Adams <[email protected]> --------- Signed-off-by: Logan Adams <[email protected]> Co-authored-by: Logan Adams <[email protected]>
Commits on Apr 20, 2025
-
Fix DeepCompile benchmark script (deepspeedai#973)
* update description of versions for deepcompile * fix deepcompile benchmark script Signed-off-by: Masahiro Tanaka <[email protected]> * fix benchmark for z1 Signed-off-by: Masahiro Tanaka <[email protected]> * add options for deepcompile bench Signed-off-by: Masahiro Tanaka <[email protected]> --------- Signed-off-by: Masahiro Tanaka <[email protected]>
Commits on May 23, 2025
-
Add example for Deepspeed-AutoTP (deepspeedai#964)
* update tp example Signed-off-by: inkcherry <[email protected]> * update Signed-off-by: inkcherry <[email protected]> * add length bench file Signed-off-by: inkcherry <[email protected]> --------- Signed-off-by: inkcherry <[email protected]> Co-authored-by: Hongwei Chen <[email protected]>
Commits on Jun 9, 2025
-
fix: Fix: Correctly define choices as tuple for reward-model arg Fixes …
…deepspeedai#941 (deepspeedai#974) Signed-off-by: Vensenmu <[email protected]>
-
DeepNVMe update (deepspeedai#966)
* Fast model checkpointing * Support both legacy and serialized formats * Add io_buffer_mb option * Bug fix * Force flush * More model options; Refactor common codes * --gpu option * --half and more flexible options * Add deepspeed.save_checkpoint() * Free ds memory * Improve repro * Double I/O buffer (deepspeedai#56) * Double I/O buffer (deepspeedai#60) * Add checkpoint comparison (deepspeedai#62) * Add checkpoint comparison * Corrected a typo Co-authored-by: Yang Li <[email protected]> * save_checkpoint perf monitoring * Disable checkpoint save on exit * Perf statistics for save_checkpoint (deepspeedai#64) * save_checkpoint perf monitoring * Disable checkpoint save on exit * add logs for a100-80 * add torch* error log with half flag but without fused flag * log for error * local rank arg * Handle local_rank arg (deepspeedai#78) * save_checkpoint perf monitoring * Disable checkpoint save on exit * local rank arg * Single writer option * Single writer option (deepspeedai#79) * save_checkpoint perf monitoring * Disable checkpoint save on exit * local rank arg * Single writer option * Allow missing folder * DP writer refactor * Update for DS; Add GDS Signed-off-by: Olatunji Ruwase <[email protected]> * Integrate GDS into deepspeed_model_save * Rebase fast persist (deepspeedai#184) * Fast model checkpointing * Support both legacy and serialized formats * Add io_buffer_mb option * Bug fix * Force flush * More model options; Refactor common codes * --gpu option * --half and more flexible options * Add deepspeed.save_checkpoint() * Free ds memory * Improve repro * Double I/O buffer (deepspeedai#56) * Double I/O buffer (deepspeedai#60) * Add checkpoint comparison (deepspeedai#62) * Add checkpoint comparison * Corrected a typo Co-authored-by: Yang Li <[email protected]> * save_checkpoint perf monitoring * Disable checkpoint save on exit * Perf statistics for save_checkpoint (deepspeedai#64) * save_checkpoint perf monitoring * Disable checkpoint save on exit * add logs for a100-80 * add torch* error log with half flag but without fused flag * log for error * local rank arg * Handle local_rank arg (deepspeedai#78) * save_checkpoint perf monitoring * Disable checkpoint save on exit * local rank arg * Single writer option * Single writer option (deepspeedai#79) * save_checkpoint perf monitoring * Disable checkpoint save on exit * local rank arg * Single writer option * Allow missing folder * DP writer refactor * Update for DS; Add GDS Signed-off-by: Olatunji Ruwase <[email protected]> * Integrate GDS into deepspeed_model_save --------- Signed-off-by: Olatunji Ruwase <[email protected]> Co-authored-by: jerryyangli <[email protected]> Co-authored-by: Yang Li <[email protected]> Co-authored-by: GuanhuaWang <[email protected]> * Move folder Signed-off-by: Olatunji Ruwase <[email protected]> * Remove folder Signed-off-by: Olatunji Ruwase <[email protected]> * More cleanup Signed-off-by: Olatunji Ruwase <[email protected]> * torch changes Signed-off-by: Olatunji Ruwase <[email protected]> * sglang+zero_inference * Remove file * Add offload configs * Add pin_memory * Cleanup scripts * SGLang README * Remove file --------- Signed-off-by: Olatunji Ruwase <[email protected]> Co-authored-by: jerryyangli <[email protected]> Co-authored-by: Yang Li <[email protected]> Co-authored-by: GuanhuaWang <[email protected]> Co-authored-by: Logan Adams <[email protected]> Co-authored-by: Hongwei Chen <[email protected]> Co-authored-by: Zhipeng Wang <[email protected]>
7 people authoredJun 9, 2025
Commits on Jun 12, 2025
-
Update domino example (deepspeedai#976)
* remove files Signed-off-by: Hongwei Chen <[email protected]> * Update domino example Signed-off-by: Hongwei Chen <[email protected]> * apply review suggestions Signed-off-by: Hongwei Chen <[email protected]> --------- Signed-off-by: Hongwei Chen <[email protected]>
Commits on Jun 18, 2025
-
Simplify and add README (deepspeedai#978)
Signed-off-by: Olatunji Ruwase <[email protected]>
Commits on Jun 21, 2025
-
Add file extension (deepspeedai#980)
Signed-off-by: Hongwei Chen <[email protected]>
Commits on Jul 4, 2025
-
Update submodule link to reflect https style (deepspeedai#981)
Signed-off-by: raviguptaamd <[email protected]>
Commits on Jul 8, 2025
-
fix init weights issue for critic/reward model (deepspeedai#983)
* Add file extension (deepspeedai#980) Signed-off-by: Hongwei Chen <[email protected]> Signed-off-by: jouw <[email protected]> * fix init weights issue for critic/reward model Signed-off-by: jouw <[email protected]> * Update submodule link to reflect https style (deepspeedai#981) Signed-off-by: raviguptaamd <[email protected]> Signed-off-by: jouw <[email protected]> * fix formatting issue Signed-off-by: jouw <[email protected]> --------- Signed-off-by: Hongwei Chen <[email protected]> Signed-off-by: jouw <[email protected]> Signed-off-by: raviguptaamd <[email protected]> Co-authored-by: Hongwei Chen <[email protected]> Co-authored-by: raviguptaamd <[email protected]>
3 people authoredJul 8, 2025
Commits on Aug 16, 2025
-
Add Benchmarking and Fine-Tuning Support for ZenFlow (deepspeedai#982)
* Add benchmark scripts and README for ZenFlow - Introduced `zf_benchmark.py` for model offloading benchmarking with DeepSpeed. - Added `output_table.py` to parse and display benchmark results in a tabular format. - Created `run_benchmark.sh` to automate benchmark runs with various configurations. Signed-off-by: Tingfeng Lan <[email protected]> * Add Llama-2 fine-tuning scripts and configuration for ZenFlow - Introduced `finetune_llama.py` for fine-tuning the Llama-2 model using DeepSpeed and ZenFlow. - Added `finetune_llama.sh` for automated training setup with environment variables and DeepSpeed command. - Added `zf_config.json` example for DeepSpeed configuration with ZenFlow optimizations. Signed-off-by: Tingfeng Lan <[email protected]> Co-authored-by: Yusen Wu <[email protected]> * Add explanation tips for interpreting benchmark results in README Signed-off-by: Tingfeng Lan <[email protected]> * Add guidance on step/latency interpretation Signed-off-by: Tingfeng Lan <[email protected]> --------- Signed-off-by: Tingfeng Lan <[email protected]> Co-authored-by: Yusen Wu <[email protected]>
Commits on Aug 20, 2025
-
Fix README for LLaMA-2 fine-tuning with ZenFlow. (deepspeedai#987)
Signed-off-by: Tingfeng Lan <[email protected]>
Commits on Sep 29, 2025
-
Superoffload examples (deepspeedai#990)
* feat: add examples for superoffload * fix: typo * fix: remove hardcoded GPU bind * feat: add requirement for superoffload
Commits on Oct 15, 2025
-
DeepNVMe benchmarks (deepspeedai#991)
* ds_io sweep scripts * Use accelerator pin memory * Credit * Add README Signed-off-by: Olatunji Ruwase <[email protected]> * Add README Signed-off-by: Olatunji Ruwase <[email protected]> --------- Signed-off-by: Olatunji Ruwase <[email protected]> Co-authored-by: Olatunji Ruwase <[email protected]>
Loading
This comparison is taking too long to generate.
Unfortunately it looks like we can’t render this comparison for you right now. It might be too big, or there might be something weird with your repository.
You can try running this command locally to see the comparison on your machine:
git diff master...master