kv-cache : remove LLAMA_SET_ROWS checks #15505
Merged
+20
−138
Conversation
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
danbev
approved these changes
Aug 22, 2025
|
The only backends that currently are going to be affected by this change are CANN and OpenCL when using quantized KV cache. With standard F16 KV cache there should be no problems. |
44933f7 to
642d79e
Compare
642d79e to
61b7fe2
Compare
4 tasks
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Aug 28, 2025
…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
…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
…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) ...
ggerganov
commented
Aug 28, 2025
| // only find a suitable slot for the ubatch. don't modify the cells yet | ||
| const auto sinfo_new = find_slot(ubatch, cont); | ||
| const auto sinfo_new = find_slot(ubatch, true); |
There was a problem hiding this comment.
This should have been false - fixing ..
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Aug 28, 2025
…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) ...
Minh141120
pushed a commit
to menloresearch/llama.cpp
that referenced
this pull request
Aug 29, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
target #15504
With the adoption of
ggml_set_rows()across all backends (#14661) we can now remove the old fallback path and simplify the implementation.