Update Operations Documentation · Workflow runs · ORippler/llama.cpp · GitHub

Actions

All workflows
Workflows
- Check Pre-Tokenizer Hashes Check Pre-Tokenizer Hashes
- Close inactive issues Close inactive issues
- Copilot Setup Steps Copilot Setup Steps
- Python check requirements.txt Python check requirements.txt
- Python Type-Check Python Type-Check
- Update Operations Documentation Update Operations Documentation
Management
- Caches

Update Operations Documentation

Actions

Loading...
Loading

update-ops-docs.yml

4 workflow runs

4 workflow runs

Hide latency of bias and gate-loading Update Operations Documentation #4: Commit 6ed6d2b pushed by ORippler

15s osimons/prefetch_gate_bias_in_fused_mmvq

osimons/prefetch_gate_bias_in_fused_mmvq

15s

Add fastdiv and fastmodulo to k_bin_bcast kernel Update Operations Documentation #3: Commit 956a1d0 pushed by ORippler

14s osimons/add_fastdiv_to_k_bin_bcast

osimons/add_fastdiv_to_k_bin_bcast

14s

Support more block_size values in rms_norm_f32 Update Operations Documentation #2: Commit bcc6c77 pushed by ORippler

10s osimons/optimize_fused_rms_norm_f32

osimons/optimize_fused_rms_norm_f32

10s

Hide memrory-latency by loop unrolling in reduce_rows_f32 Update Operations Documentation #1: Commit 7cbe50e pushed by ORippler

10s osimons/optimize_reduce_rows_f32

osimons/optimize_reduce_rows_f32

10s