Merge branch 'main' into hexwang/dsa_pcp

f3111ba

Select commit

Loading

Failed to load commit list.

Uh oh!

There was an error while loading. Please reload this page.

ATOM Test on: pull_request 12

Check Heavy CI Gate

Check Pre Checkin Signal

Load test model configs

Download aiter wheel

Accuracy (Meta-Llama-3-8B-Instruct, meta-llama/Meta-Llama-3-8B-Instruct, --kv_cache_dtype fp8 --g...

Accuracy (DeepSeek-V4-Pro, deepseek-ai/DeepSeek-V4-Pro, --kv_cache_dtype fp8 -tp 8 --hf-overrides...

Accuracy (DeepSeek-V4-Pro MTP, deepseek-ai/DeepSeek-V4-Pro, --kv_cache_dtype fp8 -tp 8 --method m...

Accuracy (gpt-oss-120b, openai/gpt-oss-120b, --kv_cache_dtype fp8 --gpu-memory-utilization 0.5, l...

Accuracy (DeepSeek-R1-0528-FP4 MTP, amd/DeepSeek-R1-0528-MXFP4-MTP-MoEFP4, --kv_cache_dtype fp8 -...

Accuracy (Qwen3-Next-80B-A3B-Thinking, Qwen/Qwen3-Next-80B-A3B-Thinking, -tp 8 --kv_cache_dtype f...

Accuracy (Kimi-K2.7-Code-MXFP4, amd/Kimi-K2.7-Code-MXFP4, --kv_cache_dtype fp8 -tp 4 --trust-remo...

Accuracy (GLM-5.2-MXFP4 MTP, amd/GLM-5.2-MXFP4, -tp 4 --online_quant_config '{"global_quant_confi...

Accuracy (Qwen3.5-397B-A17B-MXFP4, amd/Qwen3.5-397B-A17B-MXFP4, --kv_cache_dtype fp8 -tp 4 --no-e...

Accuracy (MiniMax-M3-MXFP4, amd/MiniMax-M3-MXFP4, --kv_cache_dtype fp8 -tp 8 --trust-remote-code ...

Update accuracy dashboard

ATOM SGLang Test on: pull_request 1

Check Heavy CI Gate

Check Pre Checkin Signal

Download aiter wheel

Accuracy (DeepSeek-R1-FP8 TP4)

Accuracy (DeepSeek-R1-FP4 TP4)

Accuracy (Qwen3.5-35B-A3B-FP8 TP2)

Accuracy (DeepSeek-V4-Pro TP8)

Build and Deploy Documentation on: pull_request 1

build-docs

deploy-docs

Pre Checkin on: pull_request

Check Code Style with Black

Check Code Style with Ruff

Validate accuracy catalogs against schema

Run non-GPU unit tests

ATOM vLLM Test on: pull_request 8

Check Heavy CI Gate

Check Pre Checkin Signal

Download aiter wheel

Accuracy (DeepSeek-V4-Flash TP4)

Accuracy (gpt-oss-120b TP1)

Accuracy (Kimi-K2.5-MXFP4 TP4)

Accuracy (Qwen3.5-35B-A3B-FP8 TP2)

ATOM SGLang Test on: pull_request_review 2

Check Heavy CI Gate

Check Pre Checkin Signal

Download aiter wheel

Accuracy (${{ matrix.model_name }})

ATOM vLLM Test on: pull_request_review 2

Check Heavy CI Gate

Check Pre Checkin Signal

Download aiter wheel

Accuracy (${{ matrix.display_name }})

ATOM Test on: pull_request_review 11

Check Heavy CI Gate

Check Pre Checkin Signal

Load test model configs

Download aiter wheel

Accuracy (Meta-Llama-3-8B-Instruct, meta-llama/Meta-Llama-3-8B-Instruct, --kv_cache_dtype fp8 --g...

Accuracy (DeepSeek-V4-Pro, deepseek-ai/DeepSeek-V4-Pro, --kv_cache_dtype fp8 -tp 8 --hf-overrides...

Accuracy (DeepSeek-V4-Pro MTP, deepseek-ai/DeepSeek-V4-Pro, --kv_cache_dtype fp8 -tp 8 --method m...

Accuracy (gpt-oss-120b, openai/gpt-oss-120b, --kv_cache_dtype fp8 --gpu-memory-utilization 0.5, l...

Accuracy (DeepSeek-R1-0528-FP4 MTP, amd/DeepSeek-R1-0528-MXFP4-MTP-MoEFP4, --kv_cache_dtype fp8 -...

Accuracy (Qwen3-Next-80B-A3B-Thinking, Qwen/Qwen3-Next-80B-A3B-Thinking, -tp 8 --kv_cache_dtype f...

Accuracy (Kimi-K2.7-Code-MXFP4, amd/Kimi-K2.7-Code-MXFP4, --kv_cache_dtype fp8 -tp 4 --trust-remo...

Accuracy (GLM-5.2-MXFP4 MTP, amd/GLM-5.2-MXFP4, -tp 4 --online_quant_config '{"global_quant_confi...

Accuracy (Qwen3.5-397B-A17B-MXFP4, amd/Qwen3.5-397B-A17B-MXFP4, --kv_cache_dtype fp8 -tp 4 --no-e...

Accuracy (MiniMax-M3-MXFP4, amd/MiniMax-M3-MXFP4, --kv_cache_dtype fp8 -tp 8 --trust-remote-code ...

Update accuracy dashboard

ATOM Test on: pull_request

Check Heavy CI Gate

Check Pre Checkin Signal

Load test model configs

Download aiter wheel

Accuracy

Update accuracy dashboard

ATOM vLLM Test on: pull_request

Check Heavy CI Gate

Check Pre Checkin Signal

Download aiter wheel

Accuracy (${{ matrix.display_name }})

ATOM SGLang Test on: pull_request

Check Heavy CI Gate

Check Pre Checkin Signal

Download aiter wheel

Accuracy (${{ matrix.model_name }})

Merge branch 'main' into hexwang/dsa_pcp

Uh oh!

Select a check to view from the sidebar