From 2d47b4d22b00d4618c205d86e24a29f8a5bb25d8 Mon Sep 17 00:00:00 2001
From: Cam Quilici <cjquilici@gmail.com>
Date: Mon, 20 Apr 2026 08:46:05 -0500
Subject: [PATCH] Revert "Add B300 config: kimi-k2.5-fp4-vllm (#1056)"
 [skip-sweep]

This reverts commit a35e536941a4ebc3322c409c59fa8541738438a5.
---
 .github/configs/nvidia-master.yaml          | 23 ------
 benchmarks/single_node/kimik2.5_fp4_b300.sh | 80 ---------------------
 perf-changelog.yaml                         |  8 ---
 3 files changed, 111 deletions(-)
 delete mode 100755 benchmarks/single_node/kimik2.5_fp4_b300.sh

diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml
index d6202608d..90a430b9d 100644
--- a/.github/configs/nvidia-master.yaml
+++ b/.github/configs/nvidia-master.yaml
@@ -2237,29 +2237,6 @@ kimik2.5-fp4-b200-vllm:
     - { tp: 8, ep: 1, conc-start: 4, conc-end: 4 }
     - { tp: 4, ep: 1, conc-start: 4, conc-end: 64 }
 
-# NOTE: At the time of submission, https://docs.vllm.ai/projects/recipes/en/latest/moonshotai/Kimi-K2.5.html
-# does not have a B300-specific recipe, so this config reuses the existing
-# Kimi-K2.5 FP4 B200 vLLM recipe as-is until B300-specific tuning is available.
-kimik2.5-fp4-b300-vllm:
-  image: vllm/vllm-openai:v0.19.0-cu130
-  model: nvidia/Kimi-K2.5-NVFP4
-  model-prefix: kimik2.5
-  runner: b300
-  precision: fp4
-  framework: vllm
-  multinode: false
-  seq-len-configs:
-  - isl: 1024
-    osl: 1024
-    search-space:
-    - { tp: 8, ep: 1, conc-start: 4, conc-end: 4 }
-    - { tp: 4, ep: 1, conc-start: 4, conc-end: 64 }
-  - isl: 8192
-    osl: 1024
-    search-space:
-    - { tp: 8, ep: 1, conc-start: 4, conc-end: 4 }
-    - { tp: 4, ep: 1, conc-start: 4, conc-end: 64 }
-
 dsr1-fp8-b200-sglang-mtp:
   image: lmsysorg/sglang:v0.5.9-cu130
   model: deepseek-ai/DeepSeek-R1-0528
diff --git a/benchmarks/single_node/kimik2.5_fp4_b300.sh b/benchmarks/single_node/kimik2.5_fp4_b300.sh
deleted file mode 100755
index ad636f6ed..000000000
--- a/benchmarks/single_node/kimik2.5_fp4_b300.sh
+++ /dev/null
@@ -1,80 +0,0 @@
-#!/usr/bin/env bash
-
-# NOTE: At the time of submission, https://docs.vllm.ai/projects/recipes/en/latest/moonshotai/Kimi-K2.5.html
-# does not have a B300-specific recipe, so this script reuses the existing
-# Kimi-K2.5 FP4 B200 vLLM recipe as-is until B300-specific tuning is available.
-
-source "$(dirname "$0")/../benchmark_lib.sh"
-
-check_env_vars \
-    MODEL \
-    TP \
-    CONC \
-    ISL \
-    OSL \
-    MAX_MODEL_LEN \
-    RANDOM_RANGE_RATIO \
-    RESULT_FILENAME
-
-if [[ -n "$SLURM_JOB_ID" ]]; then
-  echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
-fi
-
-hf download "$MODEL"
-
-nvidia-smi
-
-export TORCH_CUDA_ARCH_LIST="10.0"
-export PYTHONNOUSERSITE=1
-
-SERVER_LOG=/workspace/server.log
-PORT=${PORT:-8888}
-
-if [ "${EVAL_ONLY}" = "true" ]; then
-    setup_eval_context
-    MAX_MODEL_LEN="$EVAL_MAX_MODEL_LEN"
-fi
-# Start GPU monitoring (power, temperature, clocks every second)
-start_gpu_monitor
-
-set -x
-vllm serve $MODEL --host 0.0.0.0 --port $PORT \
---tensor-parallel-size=$TP \
---gpu-memory-utilization 0.90 \
---max-model-len $MAX_MODEL_LEN \
---max-num-seqs $CONC \
---reasoning-parser kimi_k2 \
---tool-call-parser kimi_k2 \
---compilation_config.pass_config.fuse_allreduce_rms true \
---no-enable-prefix-caching \
---trust-remote-code > $SERVER_LOG 2>&1 &
-
-SERVER_PID=$!
-
-# Wait for server to be ready
-wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID"
-
-pip install -q datasets pandas
-
-run_benchmark_serving \
-    --model "$MODEL" \
-    --port "$PORT" \
-    --backend vllm \
-    --input-len "$ISL" \
-    --output-len "$OSL" \
-    --random-range-ratio "$RANDOM_RANGE_RATIO" \
-    --num-prompts $(( CONC * 10 )) \
-    --max-concurrency "$CONC" \
-    --result-filename "$RESULT_FILENAME" \
-    --result-dir /workspace/ \
-    --trust-remote-code
-
-# After throughput, run evaluation only if RUN_EVAL is true
-if [ "${RUN_EVAL}" = "true" ]; then
-    run_eval --framework lm-eval --port "$PORT"
-    append_lm_eval_summary
-fi
-
-# Stop GPU monitoring
-stop_gpu_monitor
-set +x
diff --git a/perf-changelog.yaml b/perf-changelog.yaml
index 16fea938d..d3bc645be 100644
--- a/perf-changelog.yaml
+++ b/perf-changelog.yaml
@@ -1471,14 +1471,6 @@
     - "At the time of submission, https://docs.vllm.ai/projects/recipes/en/latest/MiniMax/MiniMax-M2.html does not have a B300-specific recipe, so this reuses the existing MiniMax-M2.5 FP8 B200 vLLM recipe as-is"
   pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1054
 
-- config-keys:
-    - kimik2.5-fp4-b300-vllm
-  description:
-    - "Add Kimi-K2.5 FP4 (NVFP4) B300 vLLM benchmark"
-    - "Image: vllm/vllm-openai:v0.19.0-cu130"
-    - "At the time of submission, https://docs.vllm.ai/projects/recipes/en/latest/moonshotai/Kimi-K2.5.html does not have a B300-specific recipe, so this reuses the existing Kimi-K2.5 FP4 B200 vLLM recipe as-is"
-  pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1056
-
 - config-keys:
     - gptoss-fp4-mi300x-vllm
   description: