ggml : fix AMX and add batched support#19925
Merged
angt merged 1 commit intoggml-org:masterfrom Feb 26, 2026
Merged
Conversation
llama-perplexity -hf ggml-org/Qwen3-0.6B-GGUF:Q4_0 -f wikitext-2-raw/wiki.test.raw -c 2048 -b 2048 --chunks 2 before this commit: ``` perplexity: calculating perplexity over 2 chunks, n_ctx=2048, batch_size=2048, n_seq=1 perplexity: 2.31 seconds per pass - ETA 0.07 minutes [1]17.3868,[2]22.2199, Final estimate: PPL = 22.2199 +/- 1.59692 llama_perf_context_print: load time = 878.56 ms llama_perf_context_print: prompt eval time = 2037.82 ms / 4096 tokens ( 0.50 ms per token, 2009.99 tokens per second) llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_perf_context_print: total time = 6403.17 ms / 4097 tokens llama_perf_context_print: graphs reused = 0 llama_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted | llama_memory_breakdown_print: | - Host | 845 = 318 + 224 + 302 | llama_memory_breakdown_print: | - CPU_REPACK | 288 = 288 + 0 + 0 | llama_memory_breakdown_print: | - AMX | 31 = 31 + 0 + 0 | ``` after this commit: ``` perplexity: calculating perplexity over 2 chunks, n_ctx=2048, batch_size=2048, n_seq=1 perplexity: 1.98 seconds per pass - ETA 0.05 minutes [1]17.2005,[2]21.8220, Final estimate: PPL = 21.8220 +/- 1.56485 llama_perf_context_print: load time = 719.23 ms llama_perf_context_print: prompt eval time = 1676.23 ms / 4096 tokens ( 0.41 ms per token, 2443.58 tokens per second) llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_perf_context_print: total time = 4258.74 ms / 4097 tokens llama_perf_context_print: graphs reused = 0 llama_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted | llama_memory_breakdown_print: | - Host | 845 = 318 + 224 + 302 | llama_memory_breakdown_print: | - AMX | 319 = 319 + 0 + 0 | ``` (no more CPU_REPACK) after this commit, disabling amx: ``` perplexity: calculating perplexity over 2 chunks, n_ctx=2048, batch_size=2048, n_seq=1 perplexity: 2.34 seconds per pass - ETA 0.07 minutes [1]17.2005,[2]21.8220, Final estimate: PPL = 21.8220 +/- 1.56485 llama_perf_context_print: load time = 841.91 ms llama_perf_context_print: prompt eval time = 2057.28 ms / 4096 tokens ( 0.50 ms per token, 1990.98 tokens per second) llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_perf_context_print: total time = 6454.51 ms / 4097 tokens llama_perf_context_print: graphs reused = 0 llama_memory_breakdown_print: | memory breakdown [MiB] | total free self model context compute unaccounted | llama_memory_breakdown_print: | - Host | 845 = 318 + 224 + 302 | llama_memory_breakdown_print: | - CPU_REPACK | 319 = 319 + 0 + 0 | ``` => same perplexity. Signed-off-by: Adrien Gallouët <angt@huggingface.co>
ggerganov
approved these changes
Feb 26, 2026
Comment on lines
+207
to
+224
| if (done) { | ||
| return; | ||
| } | ||
|
|
||
| static thread_local tile_config_t tc; | ||
| tile_config_t current_tc; | ||
| _tile_storeconfig(¤t_tc); | ||
|
|
||
| // load only when config changes | ||
| if (tc.palette_id == 0 || (memcmp(¤t_tc.colsb, &tc.colsb, sizeof(uint16_t) * 8) != 0 && | ||
| memcmp(¤t_tc.rows, &tc.rows, sizeof(uint8_t) * 8) != 0)) { | ||
| tc.palette_id = 1; | ||
| tc.start_row = 0; | ||
| TC_CONFIG_TILE(TMM0, 8, 64); | ||
| TC_CONFIG_TILE(TMM1, 8, 64); | ||
| TC_CONFIG_TILE(TMM2, 16, 32); | ||
| TC_CONFIG_TILE(TMM3, 16, 32); | ||
| TC_CONFIG_TILE(TMM4, 16, 64); | ||
| TC_CONFIG_TILE(TMM5, 16, 64); | ||
| TC_CONFIG_TILE(TMM6, 16, 64); | ||
| TC_CONFIG_TILE(TMM7, 16, 64); | ||
| _tile_loadconfig(&tc); | ||
| } | ||
|
|
||
| is_first_time = false; | ||
| alignas(64) tile_config_t tc = {}; | ||
| tc.palette_id = 1; | ||
| tc.start_row = 0; | ||
| tc.rows[0] = 8; tc.colsb[0] = 64; | ||
| tc.rows[1] = 8; tc.colsb[1] = 64; | ||
| tc.rows[2] = 16; tc.colsb[2] = 32; | ||
| tc.rows[3] = 16; tc.colsb[3] = 32; | ||
| tc.rows[4] = 16; tc.colsb[4] = 64; | ||
| tc.rows[5] = 16; tc.colsb[5] = 64; | ||
| tc.rows[6] = 16; tc.colsb[6] = 64; | ||
| tc.rows[7] = 16; tc.colsb[7] = 64; | ||
|
|
||
| _tile_loadconfig(&tc); | ||
| done = true; |
Member
There was a problem hiding this comment.
Not familiar with the AMX tiles, but wondering if the old logic was trying to preserve some potential existing configuration that could be coming from the user code prior to initializing ggml, and hence the _tile_storeconfig() call?
Collaborator
Author
There was a problem hiding this comment.
The old code was a generic (but broken) one, we only have one setup, so we just need to setup the tile once for each thread
github-actions
bot
added
the
ggml
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
llama-perplexity -hf ggml-org/Qwen3-0.6B-GGUF:Q4_0 -f wikitext-2-raw/wiki.test.raw -c 2048 -b 2048 --chunks 2
before this commit:
after this commit:
(no more CPU_REPACK)
after this commit, disabling amx:
=> same perplexity.