[Model] Add GPT-OSS model code and config #625
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
* fused_moe config for DSv3 on MI300X updated * Add tuning script and post processing script Signed-off-by: Randall Smith <[email protected]> * Add modification to fp8_utils for tuning Signed-off-by: Randall Smith <[email protected]> * update tuning script and add the configs Signed-off-by: Randall Smith <[email protected]> * slightly better tunings Signed-off-by: Randall Smith <[email protected]> * benchmark_moe.py is updated to generate more accurate MoE configs and a specific MoE config for DSv3 is added * Bug in sgl_moe_align_block_size() is fixed by Greg * Generate fp8_w8a8 config for MI300XHF * tunings that don't give garbage output Signed-off-by: Randall Smith <[email protected]> * More accurate tunings Signed-off-by: Randall Smith <[email protected]> * More accurate tunings and reject inaccurate configs Signed-off-by: Randall Smith <[email protected]> * add new tunings Signed-off-by: Randall Smith <[email protected]> * rename tuning script and add benchmark script to use for optimizing blockwise quant Signed-off-by: Randall Smith <[email protected]> * remove white space from file names Signed-off-by: Randall Smith <[email protected]> * remove white space from file names Signed-off-by: Randall Smith <[email protected]> * Remove some unnecessary changes Signed-off-by: Randall Smith <[email protected]> * don't use space in file names Signed-off-by: Randall Smith <[email protected]> * remove XHF tunings Signed-off-by: Randall Smith <[email protected]> * remove OAM from file name Signed-off-by: Randall Smith <[email protected]> * rmeove OAM from file names Signed-off-by: Randall Smith <[email protected]> * yapf Signed-off-by: Randall Smith <[email protected]> * update config name Signed-off-by: Randall Smith <[email protected]> * remove benchmark_moe.py changes Signed-off-by: Randall Smith <[email protected]> * remove is_contiguous Signed-off-by: Randall Smith <[email protected]> * use more recent fp8_utils.py Signed-off-by: Randall Smith <[email protected]> * remove is_contiguous Signed-off-by: Randall Smith <[email protected]> --------- Signed-off-by: Randall Smith <[email protected]> Co-authored-by: qli88 <[email protected]>
…ed to each following path for their ownership to apply (ROCm#427)
Signed-off-by: isotr0py <[email protected]>
Signed-off-by: isotr0py <[email protected]>
Upstream merge 25 02 17
* Enabling ROCm CI on MI250 machines: - correct build target - correct queue Signed-off-by: Alexei V. Ivanov <[email protected]> --------- Signed-off-by: Alexei V. Ivanov <[email protected]>
* Optimization for quantized gemm skinny sizes * lint fix * Add support for bf16/fp16 * code cleanup * code cleanup * lint fix2 * cleanup * Moved the logic into tuned gemm to preserve API compatibility --------- Co-authored-by: Gregory Shtrasberg <[email protected]> Co-authored-by: Gregory Shtrasberg <[email protected]>
* Removing gfx940 and gfx941 targets. These have been deprecated in favor of gfx942 for MI300X Signed-off-by: Gregory Shtrasberg <[email protected]> * Remove from custom kernels as well --------- Signed-off-by: Gregory Shtrasberg <[email protected]>
Signed-off-by: Divakar Verma <[email protected]>
* Advance torch commit to be past pytorch/pytorch#144942 to fix tunable ops * Make sure to use the submodule commit compatible with the main aiter commit
Signed-off-by: Sage Moore <[email protected]>
Signed-off-by: Sage Moore <[email protected]>
Signed-off-by: Sage Moore <[email protected]>
Upstream merge 25 02 24
* Using aiter branch that can be built into a whl with PREBUILD_KERNELS=1 * Using fail fast on aiter build to see compilation errors in the log since it fails silently * Check for build success without installing whl
* Using proposed fix from ROCm/aiter#115 * Build fix
Upstream merge 2025 06 23
Upstream merge 2025 06 25
Upstream merge 2025 06 30
* Updated README.md for June 24 Docker release * Added additional throughput results * Fixed some throughput results
* Minor changes to command line examples * README changes and added throughput results Still waiting on latency * Added latency results * Update README.md * Update README.md
* Update test-pipeline.yaml Disabling the "Tensorizer Test". The test is seen to generate exceptions while still reporting as successful. That needs to be verified before re-enabling the test in the production environment. Signed-off-by: Alexei V. Ivanov <[email protected]> * Fixing pre-commit complaints. Signed-off-by: Alexei V. Ivanov <[email protected]> * . Signed-off-by: Alexei V. Ivanov <[email protected]> --------- Signed-off-by: Alexei V. Ivanov <[email protected]>
…symbol exposure (vllm-project#21647)" This reverts commit 9ba1c88. Signed-off-by: Gregory Shtrasberg <[email protected]>
Upstream merge 2025 07 29
Rocm port of the official vllm commit de98252 by Woosuk Kwon
ashishtanwer
requested review from
Alexei-V-Ivanov-AMD,
shajrawi,
gshtras,
maleksan85,
sunway513,
hongxiayang,
charlifu and
mawong-amd
as code owners
ashishtanwer
changed the title
gshtras
force-pushed
the
main
branch
2 times, most recently
from
1d2c43d to
eb9d4de
Compare
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.
Rocm port of the official vllm commit
de98252 by Woosuk Kwon