Skip to content

Actions: abhijitramesh/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
11 workflow runs
11 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
ggml-webgpu: port all AOT opeartors to JIT Check Pre-Tokenizer Hashes #11: Commit d99a7c1 pushed by abhijitramesh
1m 20s port_ops_prewgsl
port_ops_prewgsl
1m 20s
readme : clarify MODEL_ENDPOINT usage (#20941) Check Pre-Tokenizer Hashes #10: Commit c9dc433 pushed by abhijitramesh
14m 44s master
master
14m 44s
ggml-webgpu: port glu pipeline to shader lib with JIT compilation Check Pre-Tokenizer Hashes #9: Commit 4b1bf6e pushed by abhijitramesh
53s port_ops_prewgsl
port_ops_prewgsl
53s
ggml-webgpu: port cpy pipline to shader lib with JIT compilation Check Pre-Tokenizer Hashes #8: Commit e79c59e pushed by abhijitramesh
1m 2s port_ops_prewgsl
port_ops_prewgsl
1m 2s
vulkan: allow graphics queue only through env var (#20599) Check Pre-Tokenizer Hashes #7: Commit 740a447 pushed by abhijitramesh
1m 0s master
master
1m 0s
ggml-webgpu: add bounds checking for over-dispatched workgroups Check Pre-Tokenizer Hashes #6: Commit 1125344 pushed by abhijitramesh
57s abhijit/webgpu-matmul-workgroup-limit
abhijit/webgpu-matmul-workgroup-limit
57s
models : fix graph splits (#19866) Check Pre-Tokenizer Hashes #5: Commit 2446419 pushed by abhijitramesh
14m 4s master
master
14m 4s
[WebGPU] Plug memory leaks and free resources on shutdown (#19315) Check Pre-Tokenizer Hashes #4: Commit 57487a6 pushed by abhijitramesh
1m 3s master
master
1m 3s
ggml: added cleanups in ggml_quantize_free (#19278) Check Pre-Tokenizer Hashes #3: Commit e9a859d pushed by abhijitramesh
1m 1s master
master
1m 1s
ggml webgpu: port binary operators to use pre-wgsl Check Pre-Tokenizer Hashes #2: Commit d1060a1 pushed by abhijitramesh
1m 0s webgpu-jit-binop-overlap
webgpu-jit-binop-overlap
1m 0s
ggml webgpu: port binary operators to use pre-wgsl Check Pre-Tokenizer Hashes #1: Commit e539fd7 pushed by abhijitramesh
51s webgpu-jit-binop-overlap
webgpu-jit-binop-overlap
51s