-
Notifications
You must be signed in to change notification settings - Fork 194
[WIP][NV] add minimaxm2.5_fp4_b300_trt.sh #1712
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
hshrivastava-droid
wants to merge
1
commit into
main
Choose a base branch
from
nv/minimaxm2.5-fp4-b300-trt-v2
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+187
−2
Open
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
150 changes: 150 additions & 0 deletions
150
benchmarks/single_node/fixed_seq_len/minimaxm2.5_fp4_b300_trt.sh
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,150 @@ | ||
| #!/usr/bin/env bash | ||
|
|
||
| # Source benchmark utilities early | ||
| source "$(dirname "$0")/../../benchmark_lib.sh" | ||
|
|
||
| check_env_vars \ | ||
| MODEL \ | ||
| TP \ | ||
| CONC \ | ||
| ISL \ | ||
| OSL \ | ||
| MAX_MODEL_LEN \ | ||
| RANDOM_RANGE_RATIO \ | ||
| RESULT_FILENAME \ | ||
| DP_ATTENTION \ | ||
| EP_SIZE | ||
|
|
||
| if [[ -n "$SLURM_JOB_ID" ]]; then | ||
| echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME" | ||
| fi | ||
|
|
||
| echo "TP: $TP, CONC: $CONC, ISL: $ISL, OSL: $OSL, EP_SIZE: $EP_SIZE, DP_ATTENTION: $DP_ATTENTION" | ||
|
|
||
| MAX_NUM_TOKENS=16384 | ||
| MAX_CAPTURE_TOKENS=$(( MAX_NUM_TOKENS < CONC * ISL ? MAX_NUM_TOKENS : CONC * ISL )) | ||
| CAPTURE_TOKENS_LIST=(1 2 4 8 12 16 24 32 48 64 96 128 192 256 384 512 768) | ||
| CAPTURE_TOKENS_LIST+=( $(seq 1024 128 2047)) | ||
| CAPTURE_TOKENS_LIST+=( $(seq 2048 256 4095)) | ||
| if [[ $MAX_CAPTURE_TOKENS -ge 4096 ]]; then | ||
| CAPTURE_TOKENS_LIST+=( $(seq 4096 512 $MAX_CAPTURE_TOKENS)) | ||
| fi | ||
| CAPTURE_TOKENS_LIST=$(printf "%s, " "${CAPTURE_TOKENS_LIST[@]}") | ||
|
|
||
| CAPTURE_BATCH_LIST=(1 2 4 8 12 ) | ||
| if [[ $CONC -ge 16 ]]; then | ||
| MAX_CAPTURE_BATCH=$(( CONC < 256 ? CONC : 255 )) | ||
| CAPTURE_BATCH_LIST+=( $(seq 16 8 $MAX_CAPTURE_BATCH )) | ||
| fi | ||
| if [[ $CONC -ge 256 ]]; then | ||
| MAX_CAPTURE_BATCH=$(( CONC < 512 ? CONC : 511 )) | ||
| CAPTURE_BATCH_LIST+=( $(seq 256 16 $MAX_CAPTURE_BATCH)) | ||
| fi | ||
| if [[ $CONC -ge 512 ]]; then | ||
| MAX_CAPTURE_BATCH=$(( CONC < 768 ? CONC : 767 )) | ||
| CAPTURE_BATCH_LIST+=( $(seq 512 32 $MAX_CAPTURE_BATCH)) | ||
| fi | ||
| if [[ $CONC -ge 1024 ]]; then | ||
| CAPTURE_BATCH_LIST+=( $(seq 768 64 $CONC)) | ||
| fi | ||
| CAPTURE_BATCH_LIST=$(printf "%s, " "${CAPTURE_BATCH_LIST[@]}") | ||
| MAX_CAPTURE_TOKENS=$(( CONC < 16 ? 4096 : MAX_NUM_TOKENS )) | ||
|
|
||
| CONFIG_FILE="minimax-fp4.yaml" | ||
| cat << EOF > $CONFIG_FILE | ||
| cuda_graph_config: | ||
| enable_padding: true | ||
| batch_sizes: [${CAPTURE_BATCH_LIST%, }] | ||
| moe_config: | ||
| backend: TRTLLM | ||
| use_low_precision_moe_combine: true | ||
| enable_attention_dp: $DP_ATTENTION | ||
| torch_compile_config: | ||
| capture_num_tokens: [${CAPTURE_TOKENS_LIST%, }] | ||
| enable_piecewise_cuda_graph: true | ||
| stream_interval: 100 | ||
| print_iter_log: true | ||
| max_num_tokens: $MAX_NUM_TOKENS | ||
| kv_cache_config: | ||
| free_gpu_memory_fraction: 0.9 | ||
| enable_block_reuse: False | ||
| dtype: fp8 | ||
| scheduler_config: | ||
| capacity_scheduler_policy: MAX_UTILIZATION | ||
| context_chunking_policy: FIRST_COME_FIRST_SERVED | ||
| nvfp4_gemm_config: | ||
| allowed_backends: | ||
| - cutlass | ||
| - cublaslt | ||
| - cutedsl | ||
| - cuda_core | ||
| max_seq_len: $MAX_MODEL_LEN | ||
| num_postprocess_workers: 4 | ||
| EOF | ||
|
|
||
| if [[ $DP_ATTENTION == true ]]; then | ||
| cat << EOF >> $CONFIG_FILE | ||
| attention_dp_config: | ||
| enable_balance: true | ||
| EOF | ||
| fi | ||
|
|
||
| # `hf download` creates the target dir if missing and is itself idempotent. | ||
| # When MODEL_PATH is unset (stand-alone runs), fall back to the HF_HUB_CACHE. | ||
| # Either way, MODEL_PATH is what the server is launched with. | ||
| if [[ -n "${MODEL_PATH:-}" ]]; then | ||
| if [[ ! -d "$MODEL_PATH" || -z "$(ls -A "$MODEL_PATH" 2>/dev/null)" ]]; then | ||
| hf download "$MODEL" --local-dir "$MODEL_PATH" | ||
| fi | ||
| else | ||
| hf download "$MODEL" | ||
| export MODEL_PATH="$MODEL" | ||
| fi | ||
|
|
||
| SERVER_LOG=/workspace/server.log | ||
| PORT=${PORT:-8888} | ||
|
|
||
| echo "Generated config file contents:" | ||
| cat $CONFIG_FILE | ||
|
|
||
| # Start GPU monitoring (power, temperature, clocks every second) | ||
| start_gpu_monitor | ||
|
|
||
| set -x | ||
|
|
||
| # Launch TRT-LLM server | ||
| mpirun -n 1 --oversubscribe --allow-run-as-root \ | ||
| trtllm-serve "$MODEL_PATH" --port=$PORT \ | ||
| --trust_remote_code \ | ||
| --backend=pytorch \ | ||
| --max_batch_size $CONC \ | ||
| --tp_size=$TP --ep_size=$EP_SIZE \ | ||
| --config=$CONFIG_FILE \ | ||
| > $SERVER_LOG 2>&1 & | ||
|
|
||
| SERVER_PID=$! | ||
|
|
||
| # Wait for server to be ready | ||
| wait_for_server_ready --port "$PORT" --server-log "$SERVER_LOG" --server-pid "$SERVER_PID" | ||
|
|
||
| run_benchmark_serving \ | ||
| --model "$MODEL" \ | ||
| --port "$PORT" \ | ||
| --backend openai \ | ||
| --input-len "$ISL" \ | ||
| --output-len "$OSL" \ | ||
| --random-range-ratio "$RANDOM_RANGE_RATIO" \ | ||
| --num-prompts $(( $CONC * 10 )) \ | ||
| --max-concurrency "$CONC" \ | ||
| --result-filename "$RESULT_FILENAME" \ | ||
| --result-dir /workspace/ | ||
|
|
||
| # After throughput, run evaluation only if RUN_EVAL is true | ||
| if [ "${RUN_EVAL}" = "true" ]; then | ||
| run_eval --framework lm-eval --port "$PORT" | ||
| append_lm_eval_summary | ||
| fi | ||
|
|
||
| # Stop GPU monitoring | ||
| stop_gpu_monitor | ||
| set +x | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Missing eval-only context setup
Medium Severity
The script writes
max_seq_lenfromMAX_MODEL_LENinto the TRT-LLM config and starts the server without anEVAL_ONLYbranch. Eval-only jobs (supported by the benchmark workflow) never callsetup_eval_context, so the server can keep a throughput-tuned context cap and fail or truncate lm-eval runs.Reviewed by Cursor Bugbot for commit 9c5522e. Configure here.