Jiajun Li 176b2eb792 Add XiaomiMiMo/MiMo-7B-RL with MTP support (#128) ...

* merge commits

* fix setting in sh

* use fa3 instead of flashInfer to avoid bug

* update params and comments for mimo-rl

2025-08-26 10:51:16 +08:00

..

models

Add XiaomiMiMo/MiMo-7B-RL with MTP support (#128)

2025-08-26 10:51:16 +08:00

run-deepseek-r1.sh

[script] increase --sglang-mem-fraction-static to 0.7

2025-08-14 20:28:57 -07:00

run-glm4-9B.sh

enable path forwarding and ray dashboard (#129)

2025-08-01 19:31:50 +08:00

run-glm4.5-355B-A32B.sh

[script] increase --sglang-mem-fraction-static to 0.7

2025-08-14 20:28:57 -07:00

run-llama3.1-8B-Instruct.sh

add llama config (#157)

2025-08-11 09:39:02 +08:00

run-llama3.2-3B-Instruct-amd.sh

[Hardware] AMD Dockerfile update and test (#158)

2025-08-23 09:09:55 +08:00

run-llama3.2-3B-Instruct.sh

add llama config (#157)

2025-08-11 09:39:02 +08:00

run-mimo-7B-rl.sh

Add XiaomiMiMo/MiMo-7B-RL with MTP support (#128)

2025-08-26 10:51:16 +08:00

run-qwen3-4B-amd.sh

[Hardware] AMD Dockerfile update and test (#158)

2025-08-23 09:09:55 +08:00

run-qwen3-4B-base-sft.sh

rename sglang_example.py to sglang_rollout.py (#134)

2025-08-04 00:44:16 +08:00

run-qwen3-4B-rf-baseline.sh

enable path forwarding and ray dashboard (#129)

2025-08-01 19:31:50 +08:00

run-qwen3-4B-rf.sh

enable path forwarding and ray dashboard (#129)

2025-08-01 19:31:50 +08:00

run-qwen3-4B.sh

[bug fix] CUDA error: invalid device ordinal when CUDA_VISIBLE_DEVICES start id is not equal to 0 (#116)

2025-08-11 14:17:57 +08:00

run-qwen3-8B-amd.sh

[Hardware] AMD Dockerfile update and test (#158)

2025-08-23 09:09:55 +08:00

run-qwen3-30B-A3B.sh

[script] increase --sglang-mem-fraction-static to 0.7

2025-08-14 20:28:57 -07:00

run-qwen3-235B-A22B-sft.sh

fix typo

2025-08-11 01:37:04 -07:00

run-qwen3-235B-A22B.sh

[script] increase --sglang-mem-fraction-static to 0.7

2025-08-14 20:28:57 -07:00