remove llama 70b (#149)

Author: functionstackx

.github/workflows/70b-tmpl.yml

@@ -37,31 +37,6 @@ on:
         default: false
 
 jobs:
-  _70b-1k1k:
-    if: ${{ inputs.run_1k1k }}
-    uses: ./.github/workflows/70b-tmpl.yml
-    secrets: inherit
-    with:
-      exp-name: '70b_1k1k'
-      isl: 1024
-      osl: 1024
-      max-model-len: 2048
-      random-range-ratio: 0.8
-      use_h100: ${{ inputs.use_h100 }}
-      use_h200: ${{ inputs.use_h200 }}
-      use_b200: ${{ inputs.use_b200 }}
-      use_mi300x: ${{ inputs.use_mi300x }}
-      use_mi325x: ${{ inputs.use_mi325x }}
-      use_mi355x: ${{ inputs.use_mi355x }}
-
-  collect-70b-1k1k-results:
-    needs: _70b-1k1k
-    if: ${{ inputs.run_1k1k && always() }}
-    uses: ./.github/workflows/collect-results.yml
-    secrets: inherit
-    with:
-      exp-name: '70b_1k1k'
-
   dsr1-1k1k:
     if: ${{ inputs.run_1k1k }}
     uses: ./.github/workflows/dsr1-tmpl.yml
@@ -112,31 +87,6 @@ jobs:
     with:
       exp-name: 'gptoss_1k1k'
 
-  _70b-8k1k:
-    if: ${{ inputs.run_8k1k }}
-    uses: ./.github/workflows/70b-tmpl.yml
-    secrets: inherit
-    with:
-      exp-name: '70b_8k1k'
-      isl: 8192
-      osl: 1024
-      max-model-len: 9216
-      random-range-ratio: 0.8
-      use_h100: ${{ inputs.use_h100 }}
-      use_h200: ${{ inputs.use_h200 }}
-      use_b200: ${{ inputs.use_b200 }}
-      use_mi300x: ${{ inputs.use_mi300x }}
-      use_mi325x: ${{ inputs.use_mi325x }}
-      use_mi355x: ${{ inputs.use_mi355x }}
-
-  collect-70b-8k1k-results:
-    needs: _70b-8k1k
-    if: ${{ inputs.run_8k1k && always() }}
-    uses: ./.github/workflows/collect-results.yml
-    secrets: inherit
-    with:
-      exp-name: '70b_8k1k'
-
   dsr1-8k1k:
     if: ${{ inputs.run_8k1k }}
     uses: ./.github/workflows/dsr1-tmpl.yml
@@ -187,31 +137,6 @@ jobs:
     with:
       exp-name: 'gptoss_8k1k'
 
-  _70b-1k8k:
-    if: ${{ inputs.run_1k8k }}
-    uses: ./.github/workflows/70b-tmpl.yml
-    secrets: inherit
-    with:
-      exp-name: '70b_1k8k'
-      isl: 1024
-      osl: 8192
-      max-model-len: 9216
-      random-range-ratio: 0.8
-      use_h100: ${{ inputs.use_h100 }}
-      use_h200: ${{ inputs.use_h200 }}
-      use_b200: ${{ inputs.use_b200 }}
-      use_mi300x: ${{ inputs.use_mi300x }}
-      use_mi325x: ${{ inputs.use_mi325x }}
-      use_mi355x: ${{ inputs.use_mi355x }}
-
-  collect-70b-1k8k-results:
-    needs: _70b-1k8k
-    if: ${{ inputs.run_1k8k && always() }}
-    uses: ./.github/workflows/collect-results.yml
-    secrets: inherit
-    with:
-      exp-name: '70b_1k8k'
-
   dsr1-1k8k:
     if: ${{ inputs.run_1k8k }}
     uses: ./.github/workflows/dsr1-tmpl.yml

.github/workflows/full-sweep-tmpl.yml

@@ -33,7 +33,6 @@ jobs:
           - 'h100-cw_0'
           - 'h100-cw_1'
         config:
-          - { image: 'vllm/vllm-openai:v0.10.2', model: 'nvidia/Llama-3.3-70B-Instruct-FP8', framework: 'vllm', precision: 'fp8', exp-name: '70b_test' }
           - { image: 'vllm/vllm-openai:v0.10.2', model: 'openai/gpt-oss-120b', framework: 'vllm', precision: 'fp4', exp-name: 'gptoss_test' }
 
     name: '${{ matrix.runner }}'
@@ -70,7 +69,6 @@ jobs:
           - 'h200-nv_2'
           - 'h200-nv_3'
         config:
-          - { image: 'vllm/vllm-openai:v0.10.2', model: 'nvidia/Llama-3.3-70B-Instruct-FP8', framework: 'vllm', precision: 'fp8', exp-name: '70b_test' }
           - { image: 'lmsysorg/sglang:v0.5.2rc2-cu126', model: 'deepseek-ai/DeepSeek-R1-0528', framework: 'sglang', precision: 'fp8', exp-name: 'dsr1_test' }
           - { image: 'vllm/vllm-openai:v0.10.2', model: 'openai/gpt-oss-120b', framework: 'vllm', precision: 'fp4', exp-name: 'gptoss_test' }
 
@@ -108,7 +106,6 @@ jobs:
           - 'h200-nv_2'
           - 'h200-nv_3'
         config:
-          - { image: 'nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2', model: 'nvidia/Llama-3.3-70B-Instruct-FP8', framework: 'trt', precision: 'fp8', exp-name: '70b_test' }
           - { image: 'nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2', model: 'deepseek-ai/DeepSeek-R1-0528', framework: 'trt', precision: 'fp8', exp-name: 'dsr1_test' }
           - { image: 'nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2', model: 'openai/gpt-oss-120b', framework: 'trt', precision: 'fp4', exp-name: 'gptoss_test' }
 
@@ -140,8 +137,6 @@ jobs:
           - 'b200-nvd_2'
           - 'b200-nvd_3'
         config:
-          - { image: 'vllm/vllm-openai:v0.10.2', model: 'nvidia/Llama-3.3-70B-Instruct-FP8', framework: 'vllm', precision: 'fp8', exp-name: '70b_test' }
-          - { image: 'vllm/vllm-openai:v0.10.2', model: 'nvidia/Llama-3.3-70B-Instruct-FP4', framework: 'vllm', precision: 'fp4', exp-name: '70b_test' }
           - { image: 'lmsysorg/sglang:v0.5.3rc1-cu129-b200', model: 'deepseek-ai/DeepSeek-R1-0528', framework: 'sglang', precision: 'fp8', exp-name: 'dsr1_test' }
           - { image: 'lmsysorg/sglang:v0.5.3rc1-cu129-b200', model: 'nvidia/DeepSeek-R1-0528-FP4', framework: 'sglang', precision: 'fp4', exp-name: 'dsr1_test' }
           - { image: 'vllm/vllm-openai:v0.10.2', model: 'openai/gpt-oss-120b', framework: 'vllm', precision: 'fp4', exp-name: 'gptoss_test' }
@@ -174,8 +169,6 @@ jobs:
           - 'b200-nb_0'
           - 'b200-nb_1'
         config:
-          - { image: 'nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2', model: 'nvidia/Llama-3.3-70B-Instruct-FP8', framework: 'trt', precision: 'fp8', exp-name: '70b_test' }
-          - { image: 'nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2', model: 'nvidia/Llama-3.3-70B-Instruct-FP4', framework: 'trt', precision: 'fp4', exp-name: '70b_test' }
           - { image: 'nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2', model: 'deepseek-ai/DeepSeek-R1-0528', framework: 'trt', precision: 'fp8', exp-name: 'dsr1_test' }
           - { image: 'nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2', model: 'nvidia/DeepSeek-R1-0528-FP4', framework: 'trt', precision: 'fp4', exp-name: 'dsr1_test' }
           - { image: 'nvcr.io#nvidia/tensorrt-llm/release:1.1.0rc2.post2', model: 'openai/gpt-oss-120b', framework: 'trt', precision: 'fp4', exp-name: 'gptoss_test' }
@@ -211,7 +204,6 @@ jobs:
           - 'mi300x-cr_0'
           - 'mi300x-oci_0'
         config:
-          - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_vllm_0.10.1_instinct_20250927_rc1', model: 'amd/Llama-3.3-70B-Instruct-FP8-KV', framework: 'vllm', precision: 'fp8', exp-name: '70b_test' }
           - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi30x-20250915', model: 'deepseek-ai/DeepSeek-R1-0528', framework: 'sglang', precision: 'fp8', exp-name: 'dsr1_test' }
           - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_vllm_0.10.1_instinct_20250927_rc1', model: 'openai/gpt-oss-120b', framework: 'vllm', precision: 'fp4', exp-name: 'gptoss_test' }
 
@@ -244,7 +236,6 @@ jobs:
           - 'mi325x-tw_2'
           - 'mi325x-tw_3'
         config:
-          - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_vllm_0.10.1_instinct_20250927_rc1', model: 'amd/Llama-3.3-70B-Instruct-FP8-KV', framework: 'vllm', precision: 'fp8', exp-name: '70b_test' }
           - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi30x-20250915', model: 'deepseek-ai/DeepSeek-R1-0528', framework: 'sglang', precision: 'fp8', exp-name: 'dsr1_test' }
           - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_vllm_0.10.1_instinct_20250927_rc1', model: 'openai/gpt-oss-120b', framework: 'vllm', precision: 'fp4', exp-name: 'gptoss_test' }
 
@@ -276,8 +267,6 @@ jobs:
           - 'mi355x-amd_2'
           - 'mi355x-amd_3'
         config:
-          - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_vllm_0.10.1_instinct_20250927_rc1', model: 'amd/Llama-3.3-70B-Instruct-FP8-KV', framework: 'vllm', precision: 'fp8', exp-name: '70b_test' }
-          - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_vllm_0.10.1_instinct_20250927_rc1', model: 'amd/Llama-3.3-70B-Instruct-MXFP4-Preview', framework: 'vllm', precision: 'fp4', exp-name: '70b_test' }
           - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi35x-20250915', model: 'deepseek-ai/DeepSeek-R1-0528', framework: 'sglang', precision: 'fp8', exp-name: 'dsr1_test' }
           - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_sgl-dev-v0.5.2-rocm7.0-mi35x-20250915', model: 'amd/DeepSeek-R1-0528-MXFP4-Preview', framework: 'sglang', precision: 'fp4', exp-name: 'dsr1_test' }
           - { image: 'rocm/7.0:rocm7.0_ubuntu_22.04_vllm_0.10.1_instinct_20250927_rc1', model: 'openai/gpt-oss-120b', framework: 'vllm', precision: 'fp4', exp-name: 'gptoss_test' }