Merge branch 'main' into ishan/moreconfigs

Author: cquil11

perf-changelog.yaml

@@ -1,93 +1,97 @@
 - config-keys:
     - 70b-fp8-*-vllm
-  description: |
-    - Add compilation-config: '{"custom_ops": ["-rms_norm", "-quant_fp8", "-silu_and_mul"]}' as
-      extra config to all benchmarks/70b_fp8_mi*.sh scripts
-    - 6-7% uplift for llama for 6/8 configs
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/95
+  description:
+    - 'Add compilation-config ''{"custom_ops": ["-rms_norm", "-quant_fp8", "-silu_and_mul"]}'' as extra config to all benchmarks/70b_fp8_mi*.sh scripts'
+    - "6-7% uplift for llama for 6/8 configs"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/95
+
 - config-keys:
     - gptoss-fp4-*-trt
-  description: |
-    - Upgrade GPT-OSS TRT images from 'release:1.1.0rc2.post2' to '1.2.0rc0.post1'
-    - Add NCCL_GRAPH_REGISTER=0 to benchmarks/gptoss_fp4_b200_trt_slurm.sh
-    - Change kv_cache_config.dtype from 'auto' to 'fp8' in benchmarks/gptoss_fp4_b200_trt_slurm.sh
-    - Remove MOE_BACKEND=CUTLASS, now just defaults to TRTLLM
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/110
+  description:
+    - "Upgrade GPT-OSS TRT images from 'release:1.1.0rc2.post2' to '1.2.0rc0.post1'"
+    - "Add NCCL_GRAPH_REGISTER=0 to benchmarks/gptoss_fp4_b200_trt_slurm.sh"
+    - "Change kv_cache_config.dtype from 'auto' to 'fp8' in benchmarks/gptoss_fp4_b200_trt_slurm.sh"
+    - "Remove MOE_BACKEND=CUTLASS, now just defaults to TRTLLM"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/110
+
 - config-keys:
     - gptoss*
     - dsr1*
-  description: |
-    - Remove Llama 70B runs to make room for multi-node disagg prefill+wideEP on 
-      h100/h200/b200/mi300/mi325/mi355
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/149
+  description:
+    - "Remove Llama 70B runs to make room for multi-node disagg prefill+wideEP on h100/h200/b200/mi300/mi325/mi355"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/149
+
 - config-keys:
     - gptoss-fp4-b200-vllm
     - gptoss-fp4-h100-vllm
     - gptoss-fp4-h200-vllm
-  description: |
-    - Upgrade vLLM from 0.10.2 to 0.11.0 for GPT-OSS NVIDIA single-node configs
-    - Adds compilation-config: '{"cudagraph_mode":"PIECEWISE"} accordingly since vLLM 0.11.0
-      requires now defaults to FULL_AND_PIECEWISE
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/159
+  description:
+    - "Upgrade vLLM from 0.10.2 to 0.11.0 for GPT-OSS NVIDIA single-node configs"
+    - 'Add compilation-config ''{"cudagraph_mode":"PIECEWISE"}'' since vLLM 0.11.0 now defaults to FULL_AND_PIECEWISE'
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/159
+
 - config-keys:
     - dsr1*
-  description: |
-    - Fixes bug where 1k8k and 8k1k full sweeps had incorrect max-model-len for DeepSeek
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/163
+  description:
+    - "Fix bug where 1k8k and 8k1k full sweeps had incorrect max-model-len for DeepSeek"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/163
+
 - config-keys:
     - dsr1-fp4-b200-sglang
     - dsr1-fp8-b200-sglang
     - dsr1-fp8-h200-sglang
-  description: |
-    - Consolidates H200 and B200 SGLang configurations to use unified v0.5.5-cu129-amd64 
-      image tag and updates deprecated SGLang server arguments to their current equivalents.
-    - --enable-flashinfer-trtllm-moe & --enable-ep-moe is no longer available in sglang so we needed to change it
-      - ep: 4 for all tp: 4 entries (3 occurrences in dsr1-fp4-b200-sglang)
-      - ep: 8 for all tp: 8 entries (6 occurrences across dsr1-fp4-b200-sglang and dsr1-fp8-b200-sglang)
-    - dsr1_fp4_b200_docker.sh: Replaced --enable-ep-moe with --ep-size $EP_SIZE and --enable-flashinfer-trtllm-moe with 
-      --moe-runner-backend flashinfer_trtllm
-    - dsr1_fp8_b200_docker.sh: Replaced --enable-flashinfer-trtllm-moe with --moe-runner-backend flashinfer_trtllm and 
-      added --ep-size $EP_SIZE
-    - launch_b200-nvd.sh: Added -e EP_SIZE to Docker run command to pass environment variable to container
-    - launch_b200-tg.sh: Added -e EP_SIZE to Docker run command to pass environment variable to container
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/204
+  description:
+    - "Consolidate H200 and B200 SGLang configurations to use unified v0.5.5-cu129-amd64 image tag"
+    - "Update deprecated SGLang server arguments to current equivalents"
+    - "Replace --enable-ep-moe with --ep-size $EP_SIZE"
+    - "Replace --enable-flashinfer-trtllm-moe with --moe-runner-backend flashinfer_trtllm"
+    - "Add -e EP_SIZE to Docker run commands in launch scripts"
+    - "Set ep:4 for all tp:4 entries, ep:8 for all tp:8 entries"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/204
+
 - config-keys:
     - gptoss-fp4-mi355x-vllm
     - gptoss-fp4-b200-vllm
-  description: |
-    - Extend concurrency to 128 for gptoss mi355x/b200 vllm configurations
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/209
+  description:
+    - "Extend concurrency to 128 for gptoss mi355x/b200 vllm configurations"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/209
+
 - config-keys:
     - gptoss-fp4-b200-trt
-  description: |
-    - Extend concurrency to 128 for gptoss b200 TRT configurations
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/233
+  description:
+    - "Extend concurrency to 128 for gptoss b200 TRT configurations"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/233
+
 - config-keys:
-    - "*gb200-sglang"
-  description: |
-    - Introducing some improvements in GB200 SGLang DSR1 submission
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/257
+    - "*gb200-dynamo-sglang"
+  description:
+    - "Introduce improvements in GB200 SGLang DSR1 submission"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/257
+
 - config-keys:
     - dsr1-fp8-h200-trt
-  description: |
-    - Update TRT image from nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc0.post1 to nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc2
-    - Increase concurrency for some configurations
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/266
+  description:
+    - "Update TRT image from nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc0.post1 to nvcr.io#nvidia/tensorrt-llm/release:1.2.0rc2"
+    - "Increase concurrency for some configurations"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/266
+
 - config-keys:
     - gptoss-fp4-b200-vllm
     - gptoss-fp4-h100-vllm
     - gptoss-fp4-h200-vllm
-  description: |
-    - Update vLLM image for NVIDIA configs from vLLM 0.11.0 to vLLM 0.11.2
-    - Adds kv-cache-dtype: fp8 to benchmarks/gptoss_fp4_b200_docker.sh
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/273
+  description:
+    - "Update vLLM image for NVIDIA configs from vLLM 0.11.0 to vLLM 0.11.2"
+    - "Add kv-cache-dtype: fp8 to benchmarks/gptoss_fp4_b200_docker.sh"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/273
+
 - config-keys:
     - dsr1-fp4-mi355x-sglang
-  description: |
-    - Updating MI355x Deepseek-R1 FP4 SGLang Image to upstream v0.5.6.post1 
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/330
+  description:
+    - "Update MI355x Deepseek-R1 FP4 SGLang Image to upstream v0.5.6.post1"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/330
+
 - config-keys:
     - gptoss-fp4-b200-trt
-  description: |
-    - Add benchmark script for GPTOSS FP4 B200 TRT-LLM
-    PR: https://github.com/InferenceMAX/InferenceMAX/pull/256
+  description:
+    - "Add benchmark script for GPTOSS FP4 B200 TRT-LLM"
+  pr-link: https://github.com/InferenceMAX/InferenceMAX/pull/256

utils/matrix_logic/validation.py

@@ -330,7 +330,8 @@ class ChangelogEntry(BaseModel):
     model_config = ConfigDict(extra="forbid", populate_by_name=True)
 
     config_keys: list[str] = Field(alias="config-keys", min_length=1)
-    description: str
+    description: list[str] = Field(min_length=1)
+    pr_link: str = Field(alias="pr-link")
 
 
 class ChangelogMetadata(BaseModel):