fsdp values

Signed-off-by: Malay Nagda <malayn@nvidia.com>

Author: malay-nagda

docs/performance-summary.md

@@ -9,7 +9,7 @@ This page provides performance benchmarks for large language models using Megatr
 - **GBS**: Global Batch Size
 - **MBS**: Micro Batch Size
 - **FSDP**: Fully Sharded Data Parallel
-  - FSDP = 1: use FSDP
+  - FSDP > 0: use FSDP with sharding group size = #GPUs / (TP × PP)
   - FSDP = 0: use DDP (Distributed Data Parallel)
 - **TP**: Tensor Parallel Size
 - **PP**: Pipeline Parallel Size
@@ -54,8 +54,8 @@ The performance data includes:
 | DGX-GB200 | 64 | NVFP4 | 256 | 1 | 8192 | 0 | 2 | 4 | 1 | 5 | n/a | 4557 | 2047 |
 | DGX-GB300 | 64 | MXFP8 | 256 | 2 | 8192 | 0 | 1 | 4 | 1 | n/a | n/a | 4798 | 2157 |
 | DGX-GB200 | 64 | MXFP8 | 256 | 1 | 8192 | 0 | 2 | 4 | 1 | 5 | n/a | 3837 | 1724 |
-| DGX-GB300 | 64 | FP8 | 256 | 2 | 8192 | 1 | 1 | 1 | 1 | n/a | n/a | 5243 | 2353 |
-| DGX-GB200 | 64 | FP8 | 256 | 2 | 8192 | 1 | 1 | 1 | 1 | n/a | n/a | 4357 | 1956 |
+| DGX-GB300 | 64 | FP8 | 256 | 2 | 8192 | 64 | 1 | 1 | 1 | n/a | n/a | 5243 | 2353 |
+| DGX-GB200 | 64 | FP8 | 256 | 2 | 8192 | 64 | 1 | 1 | 1 | n/a | n/a | 4357 | 1956 |
 | DGX-H100 | 64 | FP8 | 256 | 1 | 8192 | 0 | 4 | 8 | 1 | 5 | n/a | 1639 | 736 |
 
 #### Model: LLAMA3.1_405B
@@ -201,7 +201,7 @@ The performance data includes:
 | Model | #-GPUs | Precision | GBS | MBS | Sequence Length | FSDP | TP | PP | CP | VP | EP | GA | Tokens / sec / GPU | Model TFLOP / sec / GPU |
 |-------|--------|-----------|-----|-----|-----------------|------|----|----|----|----|----|----|-----------------------|-------------------------|
 | LLAMA3_8B | 8 | FP8-CS (FP8-MX) | 128 | 2 | 8192 | 0 | 1 | 1 | 1 | n/a | 1 | 8 | 37556 (36108) | 1933 (1858) |
-| LLAMA3_70B | 64 | FP8-CS | 256 | 2 | 8192 | 1 | 1 | 1 | 1 | 1 | 1 | 2 | 4520 | 2030 |
+| LLAMA3_70B | 64 | FP8-CS | 256 | 2 | 8192 | 64 | 1 | 1 | 1 | 1 | 1 | 2 | 4520 | 2030 |
 | LLAMA3.1_405B | 256 | FP8-CS | 1536 | 1 | 8192 | 0 | 2 | 8 | 2 | 4 | 1 | 192 | 999 | 2522 |
 | DeepSeekV3 (w/o MTP) | 256 | BF16 | 4096 | 1 | 4096 | 0 | 1 | 2 | 1 | 4 | 32 | 32 | 3848 | 961 |
 | DeepSeekV3 (w/o MTP)| 256 | FP8-MX | 4096 | 1 | 4096 | 0 | 1 | 2 | 1 | 4 | 32 | 32 | 4357 | 1088 |
@@ -214,7 +214,7 @@ The performance data includes:
 | Model | #-GPUs | Precision | GBS | MBS | Sequence Length | FSDP | TP | PP | CP | VP | EP | GA | Tokens / sec / GPU | Model TFLOP / sec / GPU |
 |-------|--------|-----------|-----|-----|-----------------|------|----|----|----|----|----|----|-----------------------|-------------------------|
 | LLAMA3_8B | 8 | FP8-CS (FP8-MX) | 128 | 2 | 8192 | 0 | 1 | 1 | 1 | n/a | 1 | 8 | 31508 (29789) | 1622 (1533) |
-| LLAMA3_70B | 64 | FP8-CS | 256 | 2 | 8192 | 1 | 1 | 1 | 1 | 1 | 1 | 2 | 4312 | 1937 |
+| LLAMA3_70B | 64 | FP8-CS | 256 | 2 | 8192 | 64 | 1 | 1 | 1 | 1 | 1 | 2 | 4312 | 1937 |
 | LLAMA3.1_405B | 256 | FP8-CS | 1536 | 1 | 8192 | 0 | 4 | 16 | 1 | 4 | 1 | 384 | 813 | 2053 |
 | DeepSeekV3 (w/o MTP) | 256 | BF16 | 4096 | 1 | 4096 | 0 | 1 | 4 | 1 | 4 | 64 | 64 | 3139 | 782 |
 | DeepSeekV3 (w/o MTP) | 256 | FP8-MX | 4096 | 1 | 4096 | 0 | 1 | 8 | 1 | 4 | 32 | 128 | 4018 | 1003 |
@@ -237,7 +237,7 @@ The performance data includes:
 
 | Model | #-GPUs | Precision | GBS | MBS | Sequence Length | FSDP | TP | PP | CP | VP | EP | GA | Tokens / sec / GPU | Model TFLOP / sec / GPU |
 |-------|--------|-----------|-----|-----|-----------------|------|----|----|----|----|----|----|-----------------------|-------------------------|
-| LLAMA3_8B | 8 | FP8-CS | 128 | 1 | 8192 | 1 | 1 | 1 | 1 | n/a | 1 | 16 | 14451 | 744 |
+| LLAMA3_8B | 8 | FP8-CS | 128 | 1 | 8192 | 8 | 1 | 1 | 1 | n/a | 1 | 16 | 14451 | 744 |
 | LLAMA3_70B | 64 | FP8-CS | 128 | 1 | 8192 | 0 | 4 | 8 | 1 | 5 | 1 | 64 | 1602 | 719 |
 | LLAMA3.1_405B | 1024 | FP8-CS | 512 | 1 | 8192 | 0 | 8 | 8 | 2 | 8 | 1 | 64 | 292 | 737 |
 | GPT OSS 120B | 64 | BF16 | 512 | 4 | 4096 | 0 | 1 | 4 | 1 | 1 | 8 | 2 | 5630 | 153 |
@@ -256,8 +256,8 @@ The performance data includes:
 | Model | #-GPUs | GBS | MBS | Sequence Length | FSDP | TP | PP | CP | VP | EP | GA | Tokens / sec / GPU | Model TFLOP / sec / GPU |
 |-------|--------|-----|-----|-----------------|------|----|----|----|----|----|----|-----------------------|-------------------------|
 | LLAMA3_8B | 8 | 128 | 2 | 8192 | 0 | 1 | 1 | 1 | n/a | 1 | 8 | 31357 (29925) | 1614 (1540) |
-| LLAMA3_70B | 64 | 128 | 2 | 8192 | 1 (0) | 1 (2) | 1 (4) | 1 | 1 (5) | 1 | 1 (16) | 3986 (3546) | 1791 (1593) |
-| LLAMA3.1_405B | 128 | 64 | 1 | 8192 | 1 (0) | 2 (4) | 1 (8) | 1 (2) | 1 (8) | 1 | 1 (32) | 729 (578) | 1840 (1458) |
+| LLAMA3_70B | 64 | 128 | 2 | 8192 | 64 (0) | 1 (2) | 1 (4) | 1 | 1 (5) | 1 | 1 (16) | 3986 (3546) | 1791 (1593) |
+| LLAMA3.1_405B | 128 | 64 | 1 | 8192 | 64 (0) | 2 (4) | 1 (8) | 1 (2) | 1 (8) | 1 | 1 (32) | 729 (578) | 1840 (1458) |
 | DeepSeekV3 (tokendrop) | 256 | 2048 | 1 | 4096 | 0 | 1 | 4 (8) | 1 | 4 (2) | 64 | 32 (64) | 3454 (2835) | 899 (738) |
 | Qwen3_30B_a3B (tokendrop) | 8 | 512 | 4 | 4096 | 0 | 1 | 1 | 1 | 1 | 8 | 16 | 22775 (23723) | 524 (546) |
 | Qwen3_235B_a22B (tokendrop) | 64 | 1024 | 1 | 4096 | 0 | 2 | 1 | 1 | 1 | 64 | 32 | 4452 (4416) | 659 (654) |
@@ -276,7 +276,7 @@ The performance data includes:
 
 | Model | #-GPUs | GBS | MBS | Sequence Length | FSDP | TP | PP | CP | VP | EP | GA | Tokens / sec / GPU | Model TFLOP / sec / GPU |
 |-------|--------|-----|-----|-----------------|------|----|----|----|----|----|----|-----------------------|-------------------------|
-| LLAMA3_8B | 8 | 128 | 1 | 8192 | 1 | 1 | 1 | 1 | n/a | 1 | 16 | 14079 | 725 |
+| LLAMA3_8B | 8 | 128 | 1 | 8192 | 8 | 1 | 1 | 1 | n/a | 1 | 16 | 14079 | 725 |
 | LLAMA3_70B | 64 | 128 | 1 | 8192 | 0 | 4 | 8 | 1 | 5 | 1 | 64 | 1619 | 727 |
 | LLAMA3.1_405B | 1024 | 512 | 1 | 8192 | 0 | 8 | 8 | 2 | 8 | 1 | 64 | 302 | 763 |
 | DeepSeekV3 (dropless) | 1024 | 8192 | 1 | 4096 | 0 | 2 | 8 | 1 | 4 | 64 | 128 | 1297 | 338 (330) |