Zhichen ZengandYueming Yuan 6ccc2cab6d [feat] Gemma-4 model support (#1232) ...

Co-authored-by: Yueming Yuan <yym022502@gmail.com>

2026-06-24 12:44:14 -07:00

..

deepseek-v3-5layer.sh

Tiny fix model config error when sourcing files (#177)

2025-11-15 18:15:21 +08:00

deepseek-v3-20layer.sh

Tiny fix model config error when sourcing files (#177)

2025-11-15 18:15:21 +08:00

deepseek-v3.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

deepseek-v4-flash-4layer.sh

deepseek v4 model support (#1181)

2026-06-04 20:12:04 -07:00

deepseek-v4-flash.sh

deepseek v4 model support (#1181)

2026-06-04 20:12:04 -07:00

deepseek-v4-pro.sh

deepseek v4 model support (#1181)

2026-06-04 20:12:04 -07:00

deepseek-v32-5layer.sh

Support DeepSeek v3.2 (#963)

2026-05-28 14:20:16 -07:00

deepseek-v32.sh

Support DeepSeek v3.2 (#963)

2026-05-28 14:20:16 -07:00

gemma-4-26b-a4b-it.sh

[feat] Gemma-4 model support (#1232)

2026-06-24 12:44:14 -07:00

gemma-4-31b-it.sh

[feat] Gemma-4 model support (#1232)

2026-06-24 12:44:14 -07:00

glm4-9B.sh

a new start

2025-10-08 23:09:54 -07:00

glm4-32B.sh

a new start

2025-10-08 23:09:54 -07:00

glm4.5-106B-A12B.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

glm4.5-355B-A32B.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

glm4.7-flash.sh

[rollout] (4.5/N) Update swe-agent-v2 example scripts using current TITO design. (#747)

2026-03-29 17:36:38 -07:00

glm5-744B-A40B_4layer.sh

[model] support GLM-5 (#626)

2026-02-27 22:16:34 -08:00

glm5-744B-A40B_20layer.sh

[model] support GLM-5 (#626)

2026-02-27 22:16:34 -08:00

glm5-744B-A40B.sh

[model] support GLM-5 (#626)

2026-02-27 22:16:34 -08:00

glm5.2-744B-A40B_5layer.sh

Support GLM-5.2 744B-A40B (#1376)

2026-06-22 13:26:51 -07:00

glm5.2-744B-A40B.sh

Support GLM-5.2 744B-A40B (#1376)

2026-06-22 13:26:51 -07:00

gpt-oss-20b.sh

[model] Add gpt-oss-20b-bf16 script (#590)

2026-03-12 15:45:19 -07:00

joyai-llm-flash.sh

Support jdopensource/JoyAI-LLM-Flash (#838)

2026-06-18 14:07:31 -07:00

kimi-k2-thinking.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

kimi-k2.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

kimi-k25_2layer.sh

CI: fix kimi-2.5 oom ci (#1346)

2026-06-15 22:17:46 -07:00

llama3.1-8B-Instruct.sh

add llama config (#157)

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

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

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

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

llama3.2-3B-Instruct.sh

add llama config (#157)

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

mimo-7B-rl.sh

update code

2025-11-15 10:25:45 +08:00

moonlight.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

nemotron-3-nano-4b.sh

Feat: NVIDIA Nemotron-3 RL support (#1033)

2026-04-30 17:57:24 -07:00

nemotron-3-nano-30b-a3b.sh

Feat: NVIDIA Nemotron-3 RL support (#1033)

2026-04-30 17:57:24 -07:00

nemotron-3-super-120b-a12b.sh

fix: expert_overlap and pp issues in nemotron-3-super (#1150)

2026-05-19 23:18:19 -07:00

qwen2.5-0.5B.sh

[test] add qwen2.5-0.5B gsm8k test script

2025-07-25 05:33:58 +00:00

qwen2.5-1.5B.sh

fix qwen2.5-1.5B model args

2025-08-13 08:11:19 -07:00

qwen2.5-3B.sh

fix: modify the rotary-base to 1000000 for consistency (#252)

2025-09-03 15:22:56 +08:00

qwen2.5-7B.sh

init

2025-06-19 11:26:58 +00:00

qwen2.5-32B.sh

init

2025-06-19 11:26:58 +00:00

qwen3-0.6B.sh

add config for qwen3-0.6B

2025-07-10 02:52:18 +00:00

qwen3-1.7B.sh

[auto-sync] update code (#383)

2026-01-02 18:42:42 -08:00

qwen3-4B-Instruct-2507.sh

Tiny fix model config error when sourcing files (#177)

2025-11-15 18:15:21 +08:00

qwen3-4B.sh

Tiny unify qwen3 instruct model variant scripts (#149)

2025-11-14 15:47:13 +08:00

qwen3-8B.sh

[auto-sync] update code (#383)

2026-01-02 18:42:42 -08:00

qwen3-14B.sh

[model] fix qwen3-14B.sh

2025-09-12 02:50:19 -07:00

qwen3-30B-A3B-5layer.sh

Parameterize num-layers in qwen3-30B-A3B model script to support 5 layer model (#765)

2026-03-20 15:08:29 +08:00

qwen3-30B-A3B.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

qwen3-32B.sh

for qwen3-32B task (#253)

2025-09-03 23:16:59 +08:00

qwen3-235B-A22B.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

qwen3-next-80B-A3B.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

qwen3.5-4B.sh

[model] Add Qwen3.5 model support (4B, 9B, 27B and 35B-A3B) (#740)

2026-03-23 16:16:27 -07:00

qwen3.5-9B.sh

[model] Add Qwen3.5 model support (4B, 9B, 27B and 35B-A3B) (#740)

2026-03-23 16:16:27 -07:00

qwen3.5-27B.sh

[model] Add Qwen3.5 model support (4B, 9B, 27B and 35B-A3B) (#740)

2026-03-23 16:16:27 -07:00

qwen3.5-35B-A3B.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00

qwen3.6-27B.sh

Feat: Qwen3.6 RL support (#1022)

2026-04-30 17:57:03 -07:00

qwen3.6-35B-A3B.sh

fix: quote $MOE_LAYER_FREQ (#1094)

2026-05-10 15:17:47 -07:00