Skip to content

graph : fix assert in memory-less build_attn #15590

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 1 commit into from
Aug 26, 2025
Merged

graph : fix assert in memory-less build_attn #15590

merged 1 commit into from
Aug 26, 2025
+1 −1

Conversation

ggerganov
Copy link
Member

cont #15586

This assert will be removed after the TODOs with tag [TAG_NO_CACHE_PAD] from #14363 are completed. For now guarantee that we are not calling this path with equal_seqs && n_seqs_unq > 1, which is guaranteed in the encode() method of llama_context:

llama.cpp/src/llama-context.cpp

Lines 780 to 784 in dc7e58d

// [TAG_NO_CACHE_PAD]
// TODO: add new split mode where we pad the input sequences so that ubatch.equal_seqs == true
const llama_ubatch ubatch = balloc->split_simple(n_tokens);

@ggerganov ggerganov merged commit 0373486 into master Aug 26, 2025
54 of 56 checks passed
@ggerganov ggerganov deleted the gg/graph-no-cache-fix-assert branch August 26, 2025 14:45
Minh141120 pushed a commit to menloresearch/llama.cpp that referenced this pull request Aug 27, 2025
@ggerganov @Minh141120
graph : fix assert in memory-less build_attn (ggml-org#15590)
de85c30 
ggml-ci
gabe-l-hart added a commit to gabe-l-hart/llama.cpp that referenced this pull request Aug 28, 2025
@gabe-l-hart
Merge remote-tracking branch 'origin/master' into gabe-l-hart/nvidia-…
05a5ce3 
…nemotron-nano-15409

* origin/master: (59 commits)
scripts: add sqlite3 check for compare-commits.sh (ggml-org#15633)
kv-cache : remove LLAMA_SET_ROWS checks (ggml-org#15505)
gguf-py: byteswapping improvements (ggml-org#12851)
cli : change log to warning to explain reason for stopping (ggml-org#15604)
model-conversion : add mmproj conversion target (ggml-org#15628)
cuda: Add cublasLt_static linking when GGML_STATIC is enabled (ggml-org#15622)
server: higher timeout for tests (ggml-org#15621)
presets : add qwen3-30B-a3b FIM (ggml-org#15616)
HIP: Enable support for ggml_backend_cuda_register_host_buffer (ggml-org#15615)
kv-cache : better estimate of n_kv for multi-sequence batches (ggml-org#15610)
CANN: refactor mask handling and improve performance in FA (ggml-org#15561)
ggml-cpu : add basic RVV support for vector f32 ops (ggml-org#15057)
common : add -m to bash completion for --model [no ci] (ggml-org#15591)
OpenCL: add fused group_norm/norm, mul, add (ggml-org#15314)
tests : fix test-opt with GGML_BACKEND_DL (ggml-org#15599)
SYCL: fix rms_norm_mul_add for tensor dim not a multiple of sg_size (ggml-org#15592)
mtmd : fix mtmd ios build (ggml-org#15579)
tests: add performance test for mul mat id (ggml-org#15543)
llamafile: PowerPC Sgemm Optimization (ggml-org#15558)
graph : fix assert in memory-less build_attn (ggml-org#15590)
...
gabe-l-hart added a commit to gabe-l-hart/llama.cpp that referenced this pull request Aug 28, 2025
@gabe-l-hart
Merge remote-tracking branch 'origin/master' into gabe-l-hart/alora-s…
37d0bd0 
…upport

* origin/master: (61 commits)
scripts: add sqlite3 check for compare-commits.sh (ggml-org#15633)
kv-cache : remove LLAMA_SET_ROWS checks (ggml-org#15505)
gguf-py: byteswapping improvements (ggml-org#12851)
cli : change log to warning to explain reason for stopping (ggml-org#15604)
model-conversion : add mmproj conversion target (ggml-org#15628)
cuda: Add cublasLt_static linking when GGML_STATIC is enabled (ggml-org#15622)
server: higher timeout for tests (ggml-org#15621)
presets : add qwen3-30B-a3b FIM (ggml-org#15616)
HIP: Enable support for ggml_backend_cuda_register_host_buffer (ggml-org#15615)
kv-cache : better estimate of n_kv for multi-sequence batches (ggml-org#15610)
CANN: refactor mask handling and improve performance in FA (ggml-org#15561)
ggml-cpu : add basic RVV support for vector f32 ops (ggml-org#15057)
common : add -m to bash completion for --model [no ci] (ggml-org#15591)
OpenCL: add fused group_norm/norm, mul, add (ggml-org#15314)
tests : fix test-opt with GGML_BACKEND_DL (ggml-org#15599)
SYCL: fix rms_norm_mul_add for tensor dim not a multiple of sg_size (ggml-org#15592)
mtmd : fix mtmd ios build (ggml-org#15579)
tests: add performance test for mul mat id (ggml-org#15543)
llamafile: PowerPC Sgemm Optimization (ggml-org#15558)
graph : fix assert in memory-less build_attn (ggml-org#15590)
...
gabe-l-hart added a commit to gabe-l-hart/llama.cpp that referenced this pull request Aug 28, 2025
@gabe-l-hart
Merge remote-tracking branch 'origin/master' into gabe-l-hart/thinkin…
e2a19d2 
…g-model-disabled-agent-prefill

* origin/master: (76 commits)
scripts: add sqlite3 check for compare-commits.sh (ggml-org#15633)
kv-cache : remove LLAMA_SET_ROWS checks (ggml-org#15505)
gguf-py: byteswapping improvements (ggml-org#12851)
cli : change log to warning to explain reason for stopping (ggml-org#15604)
model-conversion : add mmproj conversion target (ggml-org#15628)
cuda: Add cublasLt_static linking when GGML_STATIC is enabled (ggml-org#15622)
server: higher timeout for tests (ggml-org#15621)
presets : add qwen3-30B-a3b FIM (ggml-org#15616)
HIP: Enable support for ggml_backend_cuda_register_host_buffer (ggml-org#15615)
kv-cache : better estimate of n_kv for multi-sequence batches (ggml-org#15610)
CANN: refactor mask handling and improve performance in FA (ggml-org#15561)
ggml-cpu : add basic RVV support for vector f32 ops (ggml-org#15057)
common : add -m to bash completion for --model [no ci] (ggml-org#15591)
OpenCL: add fused group_norm/norm, mul, add (ggml-org#15314)
tests : fix test-opt with GGML_BACKEND_DL (ggml-org#15599)
SYCL: fix rms_norm_mul_add for tensor dim not a multiple of sg_size (ggml-org#15592)
mtmd : fix mtmd ios build (ggml-org#15579)
tests: add performance test for mul mat id (ggml-org#15543)
llamafile: PowerPC Sgemm Optimization (ggml-org#15558)
graph : fix assert in memory-less build_attn (ggml-org#15590)
...
gabe-l-hart added a commit to gabe-l-hart/llama.cpp that referenced this pull request Aug 28, 2025
@gabe-l-hart
Merge remote-tracking branch 'origin/master' into gabe-l-hart/nvidia-…
cb03b4f 
…nemotron-nano-15409

* origin/master: (59 commits)
scripts: add sqlite3 check for compare-commits.sh (ggml-org#15633)
kv-cache : remove LLAMA_SET_ROWS checks (ggml-org#15505)
gguf-py: byteswapping improvements (ggml-org#12851)
cli : change log to warning to explain reason for stopping (ggml-org#15604)
model-conversion : add mmproj conversion target (ggml-org#15628)
cuda: Add cublasLt_static linking when GGML_STATIC is enabled (ggml-org#15622)
server: higher timeout for tests (ggml-org#15621)
presets : add qwen3-30B-a3b FIM (ggml-org#15616)
HIP: Enable support for ggml_backend_cuda_register_host_buffer (ggml-org#15615)
kv-cache : better estimate of n_kv for multi-sequence batches (ggml-org#15610)
CANN: refactor mask handling and improve performance in FA (ggml-org#15561)
ggml-cpu : add basic RVV support for vector f32 ops (ggml-org#15057)
common : add -m to bash completion for --model [no ci] (ggml-org#15591)
OpenCL: add fused group_norm/norm, mul, add (ggml-org#15314)
tests : fix test-opt with GGML_BACKEND_DL (ggml-org#15599)
SYCL: fix rms_norm_mul_add for tensor dim not a multiple of sg_size (ggml-org#15592)
mtmd : fix mtmd ios build (ggml-org#15579)
tests: add performance test for mul mat id (ggml-org#15543)
llamafile: PowerPC Sgemm Optimization (ggml-org#15558)
graph : fix assert in memory-less build_attn (ggml-org#15590)
...
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@danbev danbev danbev approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@ggerganov @danbev