upload q3_1p7b_nobuf/checkpoints/gs400 (1/1)

.gitattributes

@@ -196,3 +196,4 @@ q3_1p7b_hardcd_lam0p1/checkpoints_hf_format/global_step_850/tokenizer.json filte
 q3_1p7b_hardcd_lam0p1/checkpoints/global_step_850/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 q3_1p7b_nobuf/checkpoints_hf_format/global_step_350/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 q3_1p7b_nobuf/checkpoints_hf_format/global_step_400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text

q3_1p7b_nobuf/checkpoints/global_step_400/actor/.hf_failed

@@ -0,0 +1 @@
+exit=1

q3_1p7b_nobuf/checkpoints/global_step_400/actor/extra_state_world_size_4_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401c8f9af4d1fc72bf5110315a2ab86fb54f6aa32f6f3c907683fadb0f387b70
+size 14632

q3_1p7b_nobuf/checkpoints/global_step_400/actor/extra_state_world_size_4_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9a530a49bbd426ad00667639e046c0446b8e0a4becf19b294d3ea0417e4cc2
+size 14632

q3_1p7b_nobuf/checkpoints/global_step_400/actor/extra_state_world_size_4_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94dfcf2e8811d121d5ed65afcc787da4ac0f5360a71dd909ce102f17879ddcd0
+size 14632

q3_1p7b_nobuf/checkpoints/global_step_400/actor/extra_state_world_size_4_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e68efd6fd981c1d6a91125bab1519e200ce688650ad84dad38d8516b9a0366
+size 14632

q3_1p7b_nobuf/checkpoints/global_step_400/actor/fsdp_config.json

@@ -0,0 +1,4 @@
+{
+    "FSDP_version": 1,
+    "world_size": 4
+}

q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface/config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

q3_1p7b_nobuf/checkpoints/global_step_400/actor/model_world_size_4_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dacce85e1c6a2c62b09e3b63d83e1ee6375d92bb2cd2ec442cc9971d92205fba
+size 2031921914

q3_1p7b_nobuf/checkpoints/global_step_400/actor/model_world_size_4_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8375c74294fe2a247779e67412bfa85e367b728ae5896229c1574be964f45a7f
+size 2031921914

q3_1p7b_nobuf/checkpoints/global_step_400/actor/model_world_size_4_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe31f4027e325cd0d5dadcbb31fc1971b71d21b71b9241fc37e68730faff737
+size 2031921914

q3_1p7b_nobuf/checkpoints/global_step_400/actor/model_world_size_4_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf84901d61ca1c62e78bfb052a6ce733e0ba97dedbc67caca8de52ffe48f938d
+size 2031921914

q3_1p7b_nobuf/checkpoints/global_step_400/actor/optim_world_size_4_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cb19deef69909f029f553f004aefc0a4a4d2820fc365a8b58979fb583029183
+size 3441176119

q3_1p7b_nobuf/checkpoints/global_step_400/actor/optim_world_size_4_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13bf9c44ad141d9b90b21f7e3bb408b4f5a7efc427ec09ee87506aff9397d4b9
+size 3441176119

q3_1p7b_nobuf/checkpoints/global_step_400/actor/optim_world_size_4_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd76332d1439f75534cfd4882e13429e215ed0bce98efa0cf422fe9acecbb10
+size 3441176119

q3_1p7b_nobuf/checkpoints/global_step_400/actor/optim_world_size_4_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1679f8b6c6ea7c68761cbe5bc908601fddfb0a8064b21a4378cb94e1cbfd7f88
+size 3441176119

q3_1p7b_nobuf/checkpoints/global_step_400/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc55077ebcbc2fed3f5590b2b2fb51def342dc1fde8402ed07427487955f42bf
+size 1492

q3_1p7b_nobuf/checkpoints/global_step_400/model_merger.log

@@ -0,0 +1,60 @@
+/scratch/amlt_code/verl/__init__.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
+  import pkg_resources
+config: ModelMergerConfig(operation='merge', backend='fsdp', target_dir='/mnt/output/projects/jy_intern/amlt-results/7212866003.96173-de4ce944-76ee/polaris_full_q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface', hf_upload_path=None, private=False, test_hf_dir=None, tie_word_embedding=False, is_value_model=False, local_dir='/mnt/output/projects/jy_intern/amlt-results/7212866003.96173-de4ce944-76ee/polaris_full_q3_1p7b_nobuf/checkpoints/global_step_400/actor', hf_model_config_path='/mnt/output/projects/jy_intern/amlt-results/7212866003.96173-de4ce944-76ee/polaris_full_q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface', hf_upload=False, use_cpu_initialization=False)
+Got device mesh tensor([0, 1, 2, 3], dtype=torch.int32), mesh_dim_names ('fsdp',)
+Processing model shards with 4 (4,) in total
+
+`torch_dtype` is deprecated! Use `dtype` instead!
+Saving model to /mnt/output/projects/jy_intern/amlt-results/7212866003.96173-de4ce944-76ee/polaris_full_q3_1p7b_nobuf/checkpoints/global_step_400/actor/huggingface
+[2026-08-21 23:57:17,490] [WARNING] [real_accelerator.py:162:get_accelerator] Setting accelerator to CPU. If you have GPU or other accelerator, we were unable to detect it.
+[2026-08-21 23:57:17,492] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cpu (auto detect)
+Traceback (most recent call last):
+  File "/opt/conda/envs/ptca/lib/python3.10/runpy.py", line 196, in _run_module_as_main
+    return _run_code(code, main_globals, None,
+  File "/opt/conda/envs/ptca/lib/python3.10/runpy.py", line 86, in _run_code
+    exec(code, run_globals)
+  File "/scratch/amlt_code/verl/model_merger/__main__.py", line 63, in <module>
+    main()
+  File "/scratch/amlt_code/verl/model_merger/__main__.py", line 58, in main
+    merger.merge_and_save()
+  File "/scratch/amlt_code/verl/model_merger/fsdp_model_merger.py", line 223, in merge_and_save
+    self.save_hf_model_and_tokenizer(merged_state_dict)
+  File "/scratch/amlt_code/verl/model_merger/base_model_merger.py", line 262, in save_hf_model_and_tokenizer
+    model.save_pretrained(self.config.target_dir, state_dict=state_dict)
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3897, in save_pretrained
+    model_to_save = unwrap_model(self)
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5994, in unwrap_model
+    return extract_model_from_parallel(model, **kwargs)
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/accelerate/utils/other.py", line 284, in extract_model_from_parallel
+    from deepspeed import DeepSpeedEngine
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/__init__.py", line 25, in <module>
+    from . import ops
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/ops/__init__.py", line 11, in <module>
+    from . import transformer
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/ops/transformer/__init__.py", line 7, in <module>
+    from .inference.config import DeepSpeedInferenceConfig
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/__init__.py", line 7, in <module>
+    from ....model_implementations.transformers.ds_transformer import DeepSpeedTransformerInference
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/model_implementations/__init__.py", line 6, in <module>
+    from .transformers.ds_transformer import DeepSpeedTransformerInference
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/model_implementations/transformers/ds_transformer.py", line 17, in <module>
+    from deepspeed.ops.transformer.inference.triton.mlp import TritonMLP
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/__init__.py", line 10, in <module>
+    from .ops import *
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/ops.py", line 8, in <module>
+    import deepspeed.ops.transformer.inference.triton.matmul_ext as matmul_ext
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/matmul_ext.py", line 10, in <module>
+    import deepspeed.ops.transformer.inference.triton.triton_matmul_kernel as triton_matmul_kernel
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/deepspeed/ops/transformer/inference/triton/triton_matmul_kernel.py", line 120, in <module>
+    def _fp_matmul(
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/triton/runtime/autotuner.py", line 368, in decorator
+    return Autotuner(fn, fn.arg_names, configs, key, reset_to_zero, restore_value, pre_hook=pre_hook,
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/triton/runtime/autotuner.py", line 130, in __init__
+    self.do_bench = driver.active.get_benchmarker()
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/triton/runtime/driver.py", line 23, in __getattr__
+    self._initialize_obj()
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/triton/runtime/driver.py", line 20, in _initialize_obj
+    self._obj = self._init_fn()
+  File "/opt/conda/envs/ptca/lib/python3.10/site-packages/triton/runtime/driver.py", line 8, in _create_driver
+    raise RuntimeError(f"{len(actives)} active drivers ({actives}). There should only be one.")
+RuntimeError: 0 active drivers ([]). There should only be one.